diff --git a/.gitignore b/.gitignore index c12ab77..ba4ff67 100644 --- a/.gitignore +++ b/.gitignore @@ -1,3 +1,6 @@ +# Data +data/ + # Byte-compiled / optimized / DLL files __pycache__/ *.py[cod] @@ -53,7 +56,7 @@ coverage.xml *.pot # Sphinx documentation -docs/_build/ +docs/build/ # Event stores *.events diff --git a/.travis.yml b/.travis.yml new file mode 100644 index 0000000..e0f70cb --- /dev/null +++ b/.travis.yml @@ -0,0 +1,10 @@ +language: python +python: + - "2.7" + - "3.3" + - "3.4" +# command to install dependencies +install: + - "pip install -r test/test-requirements.txt" +# command to run tests +script: nosetests diff --git a/DESCRIPTION.rst b/DESCRIPTION.rst new file mode 100644 index 0000000..898081a --- /dev/null +++ b/DESCRIPTION.rst @@ -0,0 +1,32 @@ +The SEG Y file format is one of several standards developed by the Society of Exploration Geophysicists for storing +geophysical seismic data. It is an open standard, and is controlled by the SEG Technical Standards Committee, a +non-profit organization. + +This project aims to implement an open SEG Y module in Python for transporting seismic data between SEG Y files and +Python data structures in pure Python. + + +Status +====== + +*Segpy 2* is currently in alpha, so expect rough edges. That said, it seems to broadly work and is largely feature +complete. + + +What It Does +============ + +How To Get It +============= + +*Segpy* is available on the Python Package index and can be installed with ``pip``:: + + $ pip install segpy + + +Requirements +============ + +*Segpy 2* work with Python 3.2 and higher (and 2.7 for now). For the majority of use *Segpy 2* has no external +dependencies. Optional modules with further dependencies such as *Numpy* are included in the ``segpy.ext`` package of +extras. diff --git a/GUI/demogtk.py b/GUI/demogtk.py deleted file mode 100755 index cc62fc8..0000000 --- a/GUI/demogtk.py +++ /dev/null @@ -1,105 +0,0 @@ -#!/usr/bin/env python -#Licence: GPLv2.0 -#Copyright: Dave Aitel - -import sys - -try: - import pygtk - #tell pyGTK, if possible, that we want GTKv2 - pygtk.require("2.0") -except: - print "You need to install pyGTK or GTKv2 or set your PYTHONPATH correctly" - print "try: export PYTHONPATH=/usr/local/lib/python2.2/site-packages/" - sys.exit(1) - -import gtk -import gtk.glade -import segypy - -#now we have both gtk and gtk.glade imported -#Also, we know we are running GTKv2 - -def insert_row(model,parent,firstcolumn,secondcolumn): - myiter=model.insert_after(parent,None) - model.set_value(myiter,0,firstcolumn) - model.set_value(myiter,1,secondcolumn) - return myiter - -class appgui: - def __init__(self): - """ - In this init we are going to display the main serverinfo window - """ - gladefile="project1.glade" - windowname="serverinfo" - self.wTree=gtk.glade.XML (gladefile,windowname) - #we only have one callback to register, but you could register - #any number, or use a special class that - #automatically registers all callbacks - dic = { "on_button1_clicked" : self.button1_clicked, - "on_serverinfo_destroy" : (gtk.mainquit)} - self.wTree.signal_autoconnect (dic) - - self.logwindowview=self.wTree.get_widget("textview1") - self.logwindow=gtk.TextBuffer(None) - self.logwindowview.set_buffer(self.logwindow) - - import gobject - self.treeview=self.wTree.get_widget("treeview1") - self.treemodel=gtk.TreeStore(gobject.TYPE_STRING, - gobject.TYPE_INT, - gobject.TYPE_STRING) - self.treeview.set_model(self.treemodel) - - self.treeview.set_headers_visible(True) - - renderer=gtk.CellRendererText() - column=gtk.TreeViewColumn("Name",renderer, text=0) - column.set_resizable(True) - self.treeview.append_column(column) - - renderer=gtk.CellRendererText() - column=gtk.TreeViewColumn("Description",renderer, text=1) - column.set_resizable(True) - self.treeview.append_column(column) - - self.treeview.show() - - model=self.treemodel - treeSTH=insert_row(model,None,'Segy Trace Header', '') - for key in segypy.TRACE_HEADER_DEF.keys(): - insert_row(model,treeSTH,key, 'An Empty Row') - treeSH=insert_row(model,None,'Segy Header', 'SH') - for key in segypy.HEADER_DEF.keys(): - insert_row(model,treeSH,key, 'An Empty Row') - - - - return - - - #####CALLLBACKS - def button1_clicked(self,widget): - print "button clicked" - host=self.wTree.get_widget("entry1").get_text() - port=int(self.wTree.get_widget("spinbutton1").get_value()) - if host=="": - return - import urllib - page=urllib.urlopen("http://"+host+":"+str(port)+"/") - data=page.read() - try: - #this changed in a revision of pyGTK2 - self.logwindow.insert_at_cursor(data,len(data)) - except: - self.logwindow.insert_at_cursor(data) - #print data - return - - -app=appgui() -gtk.main() - - - diff --git a/GUI/gui.py b/GUI/gui.py deleted file mode 100644 index f2b6267..0000000 --- a/GUI/gui.py +++ /dev/null @@ -1,240 +0,0 @@ -#!/usr/bin/python2.4 -# This program is free software; you can redistribute it and/or modify -# it under the terms of the GNU General Public License as published by -# the Free Software Foundation; either version 2 of the License, or -# (at your option) any later version. -# -# This program is distributed in the hope that it will be useful, -# but WITHOUT ANY WARRANTY; without even the implied warranty of -# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -# GNU General Public License for more details. -# -# You should have received a copy of the GNU General Public License -# along with this program; if not, write to the Free Software -# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. -# -# Small test to demonstrate glade.XML.signal_autoconnect on an instance -# - -import pygtk -pygtk.require('2.0') - - -import matplotlib -matplotlib.use('GTK') -from matplotlib.figure import Figure -from matplotlib.axes import Subplot -from matplotlib.backends.backend_gtk import FigureCanvasGTK, NavigationToolbar -from matplotlib.numerix import arange, sin, pi - -import Numeric as numpy - -import gtk, gtk.glade - -import segypy - - -def insert_row(model,parent,firstcolumn,secondcolumn,thirdcolumn): - myiter=model.insert_after(parent,None) - model.set_value(myiter,0,firstcolumn) - model.set_value(myiter,1,secondcolumn) - model.set_value(myiter,2,thirdcolumn) -# print secondcolumn -# return myiter - -def update_segyplot(self): - self.figure = Figure(figsize=(6,4), dpi=72) - self.axis = self.figure.add_subplot(111) - self.axis.set_xlabel('Trace Header') - self.axis.set_ylabel('Time [s]') - self.axis.set_title(self.segy[1]['filename']) - self.axis.grid(True) - self.axis.imshow(self.segy[0]) - self.canvas = FigureCanvasGTK(self.figure) # a gtk.DrawingArea - self.canvas.show() - - self.graphview = self.xml.get_widget("vbox4") - self.graphview.pack_start(self.canvas, True, True) - -def init_treeviews(self): - import gobject - - ############################################################### - # SEGYHEADER VIEW - self.treeview1 = self.xml.get_widget("treeview1") - self.treemodel1 = gtk.TreeStore(gobject.TYPE_STRING, - gobject.TYPE_STRING, - gobject.TYPE_STRING) - self.treeview1.set_model(self.treemodel1) - self.treeview1.set_headers_visible(True) - - # COLUMN 1 - renderer= gtk.CellRendererText() - self.tvcolumn1 = gtk.TreeViewColumn('Name', renderer, text=0) - self.tvcolumn1.set_resizable(True) - self.treeview1.append_column(self.tvcolumn1) - - # COLUMN 2 - renderer= gtk.CellRendererText() - self.tvcolumn2 = gtk.TreeViewColumn('Meaning', renderer, text=1) - self.tvcolumn2.set_resizable(True) - self.treeview1.append_column(self.tvcolumn2) - - # COLUMN 3 - renderer= gtk.CellRendererText() - self.tvcolumn3 = gtk.TreeViewColumn('Value', renderer, text=2) - self.tvcolumn3.set_resizable(True) - self.treeview1.append_column(self.tvcolumn3) - - ############################################################### - # SEGYHEADER VIEW - - self.treeview2 = self.xml.get_widget("treeview2") - self.treemodel2 = gtk.TreeStore(gobject.TYPE_STRING, - gobject.TYPE_STRING, - gobject.TYPE_STRING) - self.treeview2.set_model(self.treemodel2) - self.treeview2.set_headers_visible(True) - - # COLUMN 1 - renderer= gtk.CellRendererText() - self.tvcolumn1 = gtk.TreeViewColumn('Name', renderer, text=0) - self.tvcolumn1.set_resizable(True) - self.treeview2.append_column(self.tvcolumn1) - - # COLUMN 2 - renderer= gtk.CellRendererText() - self.tvcolumn2 = gtk.TreeViewColumn('Meaning', renderer, text=1) - self.tvcolumn2.set_resizable(True) - self.treeview2.append_column(self.tvcolumn2) - - # COLUMN 3 - renderer= gtk.CellRendererText() - self.tvcolumn3 = gtk.TreeViewColumn('Value', renderer, text=2) - self.tvcolumn3.set_resizable(True) - self.treeview2.append_column(self.tvcolumn3) - - -def update_segyheader(self): - import gobject - - - # INSERT INTO TREEMODEL - self.SHtree= {"init": 1} - for key in segypy.HEADER_DEF.keys(): - SHkey=segypy.HEADER_DEF[key] - if (SHkey.has_key('descr')): - descr = segypy.HEADER_DEF[key]['descr'][0][self.segy[1][key]] - else: - descr = '' - insert_row(self.treemodel1,None,key,descr,self.segy[1][key]) - - self.treeview1.show() - -def update_segytraceheader(self,itrace=1): - import gobject - - # INSERT INTO TREEMODEL - self.STHtree= {"init": 1} - for key in segypy.TRACE_HEADER_DEF.keys(): - STHkey=segypy.TRACE_HEADER_DEF[key] - if (STHkey.has_key('descr')): - try: - descr = segypy.TRACE_HEADER_DEF[key]['descr'][0][self.segy[2][key][itrace-1]] - except: - descr='Not Defined' - else: - descr = '' - insert_row(self.treemodel2,None,key,descr,self.segy[2][key][itrace-1]) - - self.treeview2.show() - - -class SimpleTest: - def __init__(self): - self.xml = gtk.glade.XML('segygui/segygui.glade') - self.xml.signal_autoconnect(self) - init_treeviews(self) - self.window1 = self.xml.get_widget("window1") - self.window1.resize(600,400) - - def on_cut1_activate(self, button): - self.hpaned1= self.xml.get_widget("hpaned1") - self.vbox3= self.xml.get_widget("vbox3") - pos = self.hpaned1.get_position() - if (pos==1): - pos=100 - self.vbox3.visible = 1 - else: - pos=1 - self.vbox3.visible = 0 - pos = self.hpaned1.set_position(pos) - print self.vbox3.visible - - #width,height = self.vbox3.get_size() - #print width,height - # self.window1.resize(400,400) - - - def on_about1_activate(self, button): - dialog = gtk.AboutDialog() - dialog.set_name("SegyPY GUI") - dialog.set_version(segypy.version.__str__()) - dialog.set_copyright("\302\251 Copyright 200x Thomas Mejer Hansen") - dialog.set_website("http://segymat.sourceforge.net/segypy/") - authors=["Thomas Mejer Hansen"] - dialog.set_authors(authors) - try: - f=open('LICENSE') - license = f.read(100000) - except IOError: - license = 'Could not read license file....'; - dialog.set_license(license) - ## Close dialog on user response - dialog.connect ("response", lambda d, r: d.destroy()) - dialog.show() - - def on_open1_activate(self, button): - dialog = gtk.FileChooserDialog("Open..", - None, - gtk.FILE_CHOOSER_ACTION_OPEN, - (gtk.STOCK_CANCEL, gtk.RESPONSE_CANCEL, - gtk.STOCK_OPEN, gtk.RESPONSE_OK)) - dialog.set_default_response(gtk.RESPONSE_OK) - - filter = gtk.FileFilter() - filter.set_name("All files") - filter.add_pattern("*") - - dialog.add_filter(filter) - filter = gtk.FileFilter() - filter.set_name("SEG-Y files") - filter.add_pattern("*.segy") - filter.add_pattern("*.sgy") - filter.add_pattern("*.seg-y") - dialog.add_filter(filter) - filter = gtk.FileFilter() - filter.set_name("SU files") - filter.add_pattern("*.su") - dialog.add_filter(filter) - response = dialog.run() - if response == gtk.RESPONSE_OK: - print dialog.get_filename(), 'selected' - filename = dialog.get_filename() - dialog.destroy() - self.segy = segypy.read_segy(filename) - - update_segyheader(self) - update_segytraceheader(self) - update_segyplot(self) - - def on_new1_activate(self, button): - self.segy = segypy.read_segy('../data_4byteINT.segy') - update_segyheader(self) - update_segytraceheader(self,1) - update_segyplot(self) - - -test = SimpleTest() - -gtk.main() diff --git a/GUI/project1.glade b/GUI/project1.glade deleted file mode 100644 index 97f8fcf..0000000 --- a/GUI/project1.glade +++ /dev/null @@ -1,192 +0,0 @@ - - - - - - - True - Server Info - GTK_WINDOW_TOPLEVEL - GTK_WIN_POS_NONE - False - True - False - True - False - False - GDK_WINDOW_TYPE_HINT_NORMAL - GDK_GRAVITY_NORTH_WEST - True - - - - - True - False - 0 - - - - True - False - 8 - - - - True - Host: - False - False - GTK_JUSTIFY_LEFT - False - False - 0.5 - 0.5 - 0 - 0 - PANGO_ELLIPSIZE_NONE - -1 - False - 0 - - - 0 - False - False - - - - - - True - True - True - True - 0 - - True - * - False - - - 0 - True - True - - - - - 0 - True - True - - - - - - True - True - 1 - 0 - False - GTK_UPDATE_ALWAYS - False - False - 80 1 65535 1 10 10 - - - 0 - False - False - - - - - - True - True - GO! - True - GTK_RELIEF_NORMAL - True - - - - 0 - False - False - - - - - - True - True - GTK_POLICY_ALWAYS - GTK_POLICY_ALWAYS - GTK_SHADOW_NONE - GTK_CORNER_TOP_LEFT - - - - True - True - True - False - True - GTK_JUSTIFY_LEFT - GTK_WRAP_NONE - True - 0 - 0 - 0 - 0 - 0 - 0 - - - - - - 0 - True - False - - - - - - True - True - GTK_POLICY_ALWAYS - GTK_POLICY_ALWAYS - GTK_SHADOW_NONE - GTK_CORNER_TOP_LEFT - - - - 130 - 226 - True - True - True - False - False - True - False - False - False - - - - - 0 - True - True - - - - - - - diff --git a/GUI/segygui/segygui.glade b/GUI/segygui/segygui.glade deleted file mode 100644 index 0a7d679..0000000 --- a/GUI/segygui/segygui.glade +++ /dev/null @@ -1,497 +0,0 @@ - - - - - - - True - Segy Viewer - GTK_WINDOW_TOPLEVEL - GTK_WIN_POS_CENTER - False - True - False - stock_chart-reorganize - True - False - False - GDK_WINDOW_TYPE_HINT_NORMAL - GDK_GRAVITY_NORTH_WEST - True - False - - - - True - False - 0 - - - - True - GTK_PACK_DIRECTION_LTR - GTK_PACK_DIRECTION_LTR - - - - True - _File - True - - - - - - - True - gtk-new - True - - - - - - - True - gtk-open - True - - - - - - - True - gtk-save - True - - - - - - - True - gtk-save-as - True - - - - - - - True - - - - - - True - gtk-quit - True - - - - - - - - - - - True - _Edit - True - - - - - - - True - Segy Header - True - - - - - - - True - Trace Header - True - - - - - - - True - gtk-cut - True - - - - - - - True - gtk-copy - True - - - - - - - True - gtk-paste - True - - - - - - - True - gtk-delete - True - - - - - - - - - - - True - _View - True - - - - - - True - _Help - True - - - - - - - True - _About - True - - - - - - - - - - 0 - False - False - - - - - - 385 - True - True - - - - True - False - 0 - - - - True - True - True - True - GTK_POS_TOP - False - False - - - - - - - - True - Plot - False - False - GTK_JUSTIFY_LEFT - False - False - 0.5 - 0.5 - 0 - 0 - PANGO_ELLIPSIZE_NONE - -1 - False - 0 - - - tab - - - - - - True - True - GTK_POLICY_ALWAYS - GTK_POLICY_ALWAYS - GTK_SHADOW_IN - GTK_CORNER_TOP_LEFT - - - - True - True - True - False - False - True - False - False - False - - - - - False - True - - - - - - True - Header - False - False - GTK_JUSTIFY_LEFT - False - False - 0.5 - 0.5 - 0 - 0 - PANGO_ELLIPSIZE_NONE - -1 - False - 0 - - - tab - - - - - - True - False - 0 - - - - True - False - 0 - - - - 15 - True - GTK_ARROW_LEFT - GTK_SHADOW_OUT - 0.5 - 0.5 - 0 - 0 - - - - 0 - True - True - - - - - - True - True - False - GTK_POS_TOP - 0 - GTK_UPDATE_DISCONTINUOUS - False - 0 0 100 0 0 0 - - - 0 - True - True - - - - - - 15 - True - GTK_ARROW_RIGHT - GTK_SHADOW_OUT - 0.5 - 0.5 - 0 - 0 - - - - 0 - True - True - - - - - 0 - False - False - - - - - - True - True - GTK_POLICY_ALWAYS - GTK_POLICY_ALWAYS - GTK_SHADOW_IN - GTK_CORNER_TOP_LEFT - - - - True - True - True - False - False - True - False - False - False - - - - - 0 - True - True - - - - - False - True - - - - - - True - Trace - False - False - GTK_JUSTIFY_LEFT - False - False - 0.5 - 0.5 - 0 - 0 - PANGO_ELLIPSIZE_NONE - -1 - False - 0 - - - tab - - - - - 0 - True - True - - - - - True - False - - - - - - True - False - 0 - - - - - - - - - - - - - - - True - True - - - - - 0 - True - True - - - - - - True - True - - - 0 - False - False - - - - - - - diff --git a/GUI/test/test.glade b/GUI/test/test.glade deleted file mode 100644 index 71c67da..0000000 --- a/GUI/test/test.glade +++ /dev/null @@ -1,251 +0,0 @@ - - - - - - - 800 - 600 - True - SegyPY GUI - GTK_WINDOW_TOPLEVEL - GTK_WIN_POS_NONE - False - True - False - True - False - False - GDK_WINDOW_TYPE_HINT_NORMAL - GDK_GRAVITY_NORTH_WEST - True - False - - - - 307 - True - True - True - 3 - 1 - False - 0 - 0 - - - - True - GTK_PACK_DIRECTION_LTR - GTK_PACK_DIRECTION_LTR - - - - True - _File - True - - - - - - - True - gtk-new - True - - - - - - - True - gtk-open - True - - - - - - - True - gtk-save - True - - - - - - - True - gtk-save-as - True - - - - - - - True - - - - - - True - gtk-quit - True - - - - - - - - - - - True - _Edit - True - - - - - - - True - gtk-cut - True - - - - - - - True - gtk-copy - True - - - - - - - True - gtk-paste - True - - - - - - - True - gtk-delete - True - - - - - - - - - - - True - _View - True - - - - - - True - _Help - True - - - - - - - True - _About - True - - - - - - - - - - 0 - 1 - 0 - 1 - fill - - - - - - - True - GTK_ORIENTATION_HORIZONTAL - GTK_TOOLBAR_BOTH - True - True - - - - - - - - - - - - - - - 0 - 1 - 1 - 2 - fill - - - - - - - True - False - 0 - - - - - - - - - - - 0 - 1 - 2 - 3 - fill - - - - - - - diff --git a/GUI/test/test.glade.bak b/GUI/test/test.glade.bak deleted file mode 100644 index 7ba9dd7..0000000 --- a/GUI/test/test.glade.bak +++ /dev/null @@ -1,250 +0,0 @@ - - - - - - - 800 - 600 - True - SegyPY GUI - GTK_WINDOW_TOPLEVEL - GTK_WIN_POS_NONE - False - True - False - True - False - False - GDK_WINDOW_TYPE_HINT_NORMAL - GDK_GRAVITY_NORTH_WEST - True - False - - - - True - True - True - 3 - 1 - False - 0 - 0 - - - - True - GTK_PACK_DIRECTION_LTR - GTK_PACK_DIRECTION_LTR - - - - True - _File - True - - - - - - - True - gtk-new - True - - - - - - - True - gtk-open - True - - - - - - - True - gtk-save - True - - - - - - - True - gtk-save-as - True - - - - - - - True - - - - - - True - gtk-quit - True - - - - - - - - - - - True - _Edit - True - - - - - - - True - gtk-cut - True - - - - - - - True - gtk-copy - True - - - - - - - True - gtk-paste - True - - - - - - - True - gtk-delete - True - - - - - - - - - - - True - _View - True - - - - - - True - _Help - True - - - - - - - True - _About - True - - - - - - - - - - 0 - 1 - 0 - 1 - fill - - - - - - - True - GTK_ORIENTATION_HORIZONTAL - GTK_TOOLBAR_BOTH - True - True - - - - - - - - - - - - - - - 0 - 1 - 1 - 2 - fill - - - - - - - True - False - 0 - - - - - - - - - - - 0 - 1 - 2 - 3 - fill - - - - - - - diff --git a/GUI/test/test.gladep b/GUI/test/test.gladep deleted file mode 100644 index 0d232b1..0000000 --- a/GUI/test/test.gladep +++ /dev/null @@ -1,8 +0,0 @@ - - - - - Test - test - FALSE - diff --git a/GUI/test/test.gladep.bak b/GUI/test/test.gladep.bak deleted file mode 100644 index 0d232b1..0000000 --- a/GUI/test/test.gladep.bak +++ /dev/null @@ -1,8 +0,0 @@ - - - - - Test - test - FALSE - diff --git a/README.rst b/README.rst index c0ec3fb..14c276d 100644 --- a/README.rst +++ b/README.rst @@ -1,34 +1,28 @@ -===== -Segpy -===== +======= +Segpy 2 +======= + +Status +====== + +Build status: rewrite branch: + +.. image:: https://travis-ci.org/rob-smallshire/segpy.svg?branch=rewrite + :target: https://travis-ci.org/rob-smallshire/segpy + +What is Segpy? +============== The SEG Y file format is one of several standards developed by the Society of Exploration Geophysicists for storing geophysical seismic data. It is an open standard, and is controlled by the SEG Technical Standards Committee, a non-profit organization. This project aims to implement an open SEG Y module in Python for transporting seismic data between SEG Y files and -Numpy arrays. Segpy is a package for reading, writing and manipulating SEG Y data in pure Python. +Python data structures in pure Python. -History -======= +Segpy Versions +============== -Segpy is a fork of a seemingly abandoned Python SEG Y reader called `SegyPY `_ -which was last updated in 2005. I couldn't get a response from the original author of SegyPY and since it the code was -under an LGPL license I took the decision in 2011 to fork and run a new project on Google Code, under a the name of -*Segpy* avoid confusion. In July 2014 the project was again migrated from a now defunct Mercurial repository on Google -Code to this Git repository on GitHub. - -The aim of the revived project is to fix serious problems with the code base in the area of correctness and -performance, but also to update it to work with contemporary Python environments including Python 2.7 and Python 3. - -**Pull requests, bug reports and suggestions for improvements are most welcome!** - - -Authors -======= - - * Robert Smallshire 2011 to date - * Thomas Mejer Hansen 2005 - -The Ibm2Ieee conversion routines are developed and made availabe for SegyPY by Secchi Angelo, who thanks Howard -Lightstone and Anton Vredegoor for their help. +Segpy 2.0 is a complete re-imagining of a SEG Y reader in Python and represents a complete break from Segpy 1.0 in terms +of the interface it presents to clients and the implementation behind those interfaces. Segpy 1.0 should be considered +unmaintained legacy software. The present and future of Segpy is Segpy 2. \ No newline at end of file diff --git a/docs/Makefile b/docs/Makefile new file mode 100644 index 0000000..06e2d28 --- /dev/null +++ b/docs/Makefile @@ -0,0 +1,177 @@ +# Makefile for Sphinx documentation +# + +# You can set these variables from the command line. +SPHINXOPTS = +SPHINXBUILD = sphinx-build +PAPER = +BUILDDIR = build + +# User-friendly check for sphinx-build +ifeq ($(shell which $(SPHINXBUILD) >/dev/null 2>&1; echo $$?), 1) +$(error The '$(SPHINXBUILD)' command was not found. Make sure you have Sphinx installed, then set the SPHINXBUILD environment variable to point to the full path of the '$(SPHINXBUILD)' executable. Alternatively you can add the directory with the executable to your PATH. If you don't have Sphinx installed, grab it from http://sphinx-doc.org/) +endif + +# Internal variables. +PAPEROPT_a4 = -D latex_paper_size=a4 +PAPEROPT_letter = -D latex_paper_size=letter +ALLSPHINXOPTS = -d $(BUILDDIR)/doctrees $(PAPEROPT_$(PAPER)) $(SPHINXOPTS) source +# the i18n builder cannot share the environment and doctrees with the others +I18NSPHINXOPTS = $(PAPEROPT_$(PAPER)) $(SPHINXOPTS) source + +.PHONY: help clean html dirhtml singlehtml pickle json htmlhelp qthelp devhelp epub latex latexpdf text man changes linkcheck doctest gettext + +help: + @echo "Please use \`make ' where is one of" + @echo " html to make standalone HTML files" + @echo " dirhtml to make HTML files named index.html in directories" + @echo " singlehtml to make a single large HTML file" + @echo " pickle to make pickle files" + @echo " json to make JSON files" + @echo " htmlhelp to make HTML files and a HTML help project" + @echo " qthelp to make HTML files and a qthelp project" + @echo " devhelp to make HTML files and a Devhelp project" + @echo " epub to make an epub" + @echo " latex to make LaTeX files, you can set PAPER=a4 or PAPER=letter" + @echo " latexpdf to make LaTeX files and run them through pdflatex" + @echo " latexpdfja to make LaTeX files and run them through platex/dvipdfmx" + @echo " text to make text files" + @echo " man to make manual pages" + @echo " texinfo to make Texinfo files" + @echo " info to make Texinfo files and run them through makeinfo" + @echo " gettext to make PO message catalogs" + @echo " changes to make an overview of all changed/added/deprecated items" + @echo " xml to make Docutils-native XML files" + @echo " pseudoxml to make pseudoxml-XML files for display purposes" + @echo " linkcheck to check all external links for integrity" + @echo " doctest to run all doctests embedded in the documentation (if enabled)" + +clean: + rm -rf $(BUILDDIR)/* + +html: + $(SPHINXBUILD) -b html $(ALLSPHINXOPTS) $(BUILDDIR)/html + @echo + @echo "Build finished. The HTML pages are in $(BUILDDIR)/html." + +dirhtml: + $(SPHINXBUILD) -b dirhtml $(ALLSPHINXOPTS) $(BUILDDIR)/dirhtml + @echo + @echo "Build finished. The HTML pages are in $(BUILDDIR)/dirhtml." + +singlehtml: + $(SPHINXBUILD) -b singlehtml $(ALLSPHINXOPTS) $(BUILDDIR)/singlehtml + @echo + @echo "Build finished. The HTML page is in $(BUILDDIR)/singlehtml." + +pickle: + $(SPHINXBUILD) -b pickle $(ALLSPHINXOPTS) $(BUILDDIR)/pickle + @echo + @echo "Build finished; now you can process the pickle files." + +json: + $(SPHINXBUILD) -b json $(ALLSPHINXOPTS) $(BUILDDIR)/json + @echo + @echo "Build finished; now you can process the JSON files." + +htmlhelp: + $(SPHINXBUILD) -b htmlhelp $(ALLSPHINXOPTS) $(BUILDDIR)/htmlhelp + @echo + @echo "Build finished; now you can run HTML Help Workshop with the" \ + ".hhp project file in $(BUILDDIR)/htmlhelp." + +qthelp: + $(SPHINXBUILD) -b qthelp $(ALLSPHINXOPTS) $(BUILDDIR)/qthelp + @echo + @echo "Build finished; now you can run "qcollectiongenerator" with the" \ + ".qhcp project file in $(BUILDDIR)/qthelp, like this:" + @echo "# qcollectiongenerator $(BUILDDIR)/qthelp/Segpy.qhcp" + @echo "To view the help file:" + @echo "# assistant -collectionFile $(BUILDDIR)/qthelp/Segpy.qhc" + +devhelp: + $(SPHINXBUILD) -b devhelp $(ALLSPHINXOPTS) $(BUILDDIR)/devhelp + @echo + @echo "Build finished." + @echo "To view the help file:" + @echo "# mkdir -p $$HOME/.local/share/devhelp/Segpy" + @echo "# ln -s $(BUILDDIR)/devhelp $$HOME/.local/share/devhelp/Segpy" + @echo "# devhelp" + +epub: + $(SPHINXBUILD) -b epub $(ALLSPHINXOPTS) $(BUILDDIR)/epub + @echo + @echo "Build finished. The epub file is in $(BUILDDIR)/epub." + +latex: + $(SPHINXBUILD) -b latex $(ALLSPHINXOPTS) $(BUILDDIR)/latex + @echo + @echo "Build finished; the LaTeX files are in $(BUILDDIR)/latex." + @echo "Run \`make' in that directory to run these through (pdf)latex" \ + "(use \`make latexpdf' here to do that automatically)." + +latexpdf: + $(SPHINXBUILD) -b latex $(ALLSPHINXOPTS) $(BUILDDIR)/latex + @echo "Running LaTeX files through pdflatex..." + $(MAKE) -C $(BUILDDIR)/latex all-pdf + @echo "pdflatex finished; the PDF files are in $(BUILDDIR)/latex." + +latexpdfja: + $(SPHINXBUILD) -b latex $(ALLSPHINXOPTS) $(BUILDDIR)/latex + @echo "Running LaTeX files through platex and dvipdfmx..." + $(MAKE) -C $(BUILDDIR)/latex all-pdf-ja + @echo "pdflatex finished; the PDF files are in $(BUILDDIR)/latex." + +text: + $(SPHINXBUILD) -b text $(ALLSPHINXOPTS) $(BUILDDIR)/text + @echo + @echo "Build finished. The text files are in $(BUILDDIR)/text." + +man: + $(SPHINXBUILD) -b man $(ALLSPHINXOPTS) $(BUILDDIR)/man + @echo + @echo "Build finished. The manual pages are in $(BUILDDIR)/man." + +texinfo: + $(SPHINXBUILD) -b texinfo $(ALLSPHINXOPTS) $(BUILDDIR)/texinfo + @echo + @echo "Build finished. The Texinfo files are in $(BUILDDIR)/texinfo." + @echo "Run \`make' in that directory to run these through makeinfo" \ + "(use \`make info' here to do that automatically)." + +info: + $(SPHINXBUILD) -b texinfo $(ALLSPHINXOPTS) $(BUILDDIR)/texinfo + @echo "Running Texinfo files through makeinfo..." + make -C $(BUILDDIR)/texinfo info + @echo "makeinfo finished; the Info files are in $(BUILDDIR)/texinfo." + +gettext: + $(SPHINXBUILD) -b gettext $(I18NSPHINXOPTS) $(BUILDDIR)/locale + @echo + @echo "Build finished. The message catalogs are in $(BUILDDIR)/locale." + +changes: + $(SPHINXBUILD) -b changes $(ALLSPHINXOPTS) $(BUILDDIR)/changes + @echo + @echo "The overview file is in $(BUILDDIR)/changes." + +linkcheck: + $(SPHINXBUILD) -b linkcheck $(ALLSPHINXOPTS) $(BUILDDIR)/linkcheck + @echo + @echo "Link check complete; look for any errors in the above output " \ + "or in $(BUILDDIR)/linkcheck/output.txt." + +doctest: + $(SPHINXBUILD) -b doctest $(ALLSPHINXOPTS) $(BUILDDIR)/doctest + @echo "Testing of doctests in the sources finished, look at the " \ + "results in $(BUILDDIR)/doctest/output.txt." + +xml: + $(SPHINXBUILD) -b xml $(ALLSPHINXOPTS) $(BUILDDIR)/xml + @echo + @echo "Build finished. The XML files are in $(BUILDDIR)/xml." + +pseudoxml: + $(SPHINXBUILD) -b pseudoxml $(ALLSPHINXOPTS) $(BUILDDIR)/pseudoxml + @echo + @echo "Build finished. The pseudo-XML files are in $(BUILDDIR)/pseudoxml." diff --git a/docs/docs-requirements.txt b/docs/docs-requirements.txt new file mode 100644 index 0000000..8213302 --- /dev/null +++ b/docs/docs-requirements.txt @@ -0,0 +1,2 @@ +sphinx +sphinx_rtd_theme diff --git a/docs/make.bat b/docs/make.bat new file mode 100644 index 0000000..0f7bbf1 --- /dev/null +++ b/docs/make.bat @@ -0,0 +1,242 @@ +@ECHO OFF + +REM Command file for Sphinx documentation + +if "%SPHINXBUILD%" == "" ( + set SPHINXBUILD=sphinx-build +) +set BUILDDIR=build +set ALLSPHINXOPTS=-d %BUILDDIR%/doctrees %SPHINXOPTS% source +set I18NSPHINXOPTS=%SPHINXOPTS% source +if NOT "%PAPER%" == "" ( + set ALLSPHINXOPTS=-D latex_paper_size=%PAPER% %ALLSPHINXOPTS% + set I18NSPHINXOPTS=-D latex_paper_size=%PAPER% %I18NSPHINXOPTS% +) + +if "%1" == "" goto help + +if "%1" == "help" ( + :help + echo.Please use `make ^` where ^ is one of + echo. html to make standalone HTML files + echo. dirhtml to make HTML files named index.html in directories + echo. singlehtml to make a single large HTML file + echo. pickle to make pickle files + echo. json to make JSON files + echo. htmlhelp to make HTML files and a HTML help project + echo. qthelp to make HTML files and a qthelp project + echo. devhelp to make HTML files and a Devhelp project + echo. epub to make an epub + echo. latex to make LaTeX files, you can set PAPER=a4 or PAPER=letter + echo. text to make text files + echo. man to make manual pages + echo. texinfo to make Texinfo files + echo. gettext to make PO message catalogs + echo. changes to make an overview over all changed/added/deprecated items + echo. xml to make Docutils-native XML files + echo. pseudoxml to make pseudoxml-XML files for display purposes + echo. linkcheck to check all external links for integrity + echo. doctest to run all doctests embedded in the documentation if enabled + goto end +) + +if "%1" == "clean" ( + for /d %%i in (%BUILDDIR%\*) do rmdir /q /s %%i + del /q /s %BUILDDIR%\* + goto end +) + + +%SPHINXBUILD% 2> nul +if errorlevel 9009 ( + echo. + echo.The 'sphinx-build' command was not found. Make sure you have Sphinx + echo.installed, then set the SPHINXBUILD environment variable to point + echo.to the full path of the 'sphinx-build' executable. Alternatively you + echo.may add the Sphinx directory to PATH. + echo. + echo.If you don't have Sphinx installed, grab it from + echo.http://sphinx-doc.org/ + exit /b 1 +) + +if "%1" == "html" ( + %SPHINXBUILD% -b html %ALLSPHINXOPTS% %BUILDDIR%/html + if errorlevel 1 exit /b 1 + echo. + echo.Build finished. The HTML pages are in %BUILDDIR%/html. + goto end +) + +if "%1" == "dirhtml" ( + %SPHINXBUILD% -b dirhtml %ALLSPHINXOPTS% %BUILDDIR%/dirhtml + if errorlevel 1 exit /b 1 + echo. + echo.Build finished. The HTML pages are in %BUILDDIR%/dirhtml. + goto end +) + +if "%1" == "singlehtml" ( + %SPHINXBUILD% -b singlehtml %ALLSPHINXOPTS% %BUILDDIR%/singlehtml + if errorlevel 1 exit /b 1 + echo. + echo.Build finished. The HTML pages are in %BUILDDIR%/singlehtml. + goto end +) + +if "%1" == "pickle" ( + %SPHINXBUILD% -b pickle %ALLSPHINXOPTS% %BUILDDIR%/pickle + if errorlevel 1 exit /b 1 + echo. + echo.Build finished; now you can process the pickle files. + goto end +) + +if "%1" == "json" ( + %SPHINXBUILD% -b json %ALLSPHINXOPTS% %BUILDDIR%/json + if errorlevel 1 exit /b 1 + echo. + echo.Build finished; now you can process the JSON files. + goto end +) + +if "%1" == "htmlhelp" ( + %SPHINXBUILD% -b htmlhelp %ALLSPHINXOPTS% %BUILDDIR%/htmlhelp + if errorlevel 1 exit /b 1 + echo. + echo.Build finished; now you can run HTML Help Workshop with the ^ +.hhp project file in %BUILDDIR%/htmlhelp. + goto end +) + +if "%1" == "qthelp" ( + %SPHINXBUILD% -b qthelp %ALLSPHINXOPTS% %BUILDDIR%/qthelp + if errorlevel 1 exit /b 1 + echo. + echo.Build finished; now you can run "qcollectiongenerator" with the ^ +.qhcp project file in %BUILDDIR%/qthelp, like this: + echo.^> qcollectiongenerator %BUILDDIR%\qthelp\Segpy.qhcp + echo.To view the help file: + echo.^> assistant -collectionFile %BUILDDIR%\qthelp\Segpy.ghc + goto end +) + +if "%1" == "devhelp" ( + %SPHINXBUILD% -b devhelp %ALLSPHINXOPTS% %BUILDDIR%/devhelp + if errorlevel 1 exit /b 1 + echo. + echo.Build finished. + goto end +) + +if "%1" == "epub" ( + %SPHINXBUILD% -b epub %ALLSPHINXOPTS% %BUILDDIR%/epub + if errorlevel 1 exit /b 1 + echo. + echo.Build finished. The epub file is in %BUILDDIR%/epub. + goto end +) + +if "%1" == "latex" ( + %SPHINXBUILD% -b latex %ALLSPHINXOPTS% %BUILDDIR%/latex + if errorlevel 1 exit /b 1 + echo. + echo.Build finished; the LaTeX files are in %BUILDDIR%/latex. + goto end +) + +if "%1" == "latexpdf" ( + %SPHINXBUILD% -b latex %ALLSPHINXOPTS% %BUILDDIR%/latex + cd %BUILDDIR%/latex + make all-pdf + cd %BUILDDIR%/.. + echo. + echo.Build finished; the PDF files are in %BUILDDIR%/latex. + goto end +) + +if "%1" == "latexpdfja" ( + %SPHINXBUILD% -b latex %ALLSPHINXOPTS% %BUILDDIR%/latex + cd %BUILDDIR%/latex + make all-pdf-ja + cd %BUILDDIR%/.. + echo. + echo.Build finished; the PDF files are in %BUILDDIR%/latex. + goto end +) + +if "%1" == "text" ( + %SPHINXBUILD% -b text %ALLSPHINXOPTS% %BUILDDIR%/text + if errorlevel 1 exit /b 1 + echo. + echo.Build finished. The text files are in %BUILDDIR%/text. + goto end +) + +if "%1" == "man" ( + %SPHINXBUILD% -b man %ALLSPHINXOPTS% %BUILDDIR%/man + if errorlevel 1 exit /b 1 + echo. + echo.Build finished. The manual pages are in %BUILDDIR%/man. + goto end +) + +if "%1" == "texinfo" ( + %SPHINXBUILD% -b texinfo %ALLSPHINXOPTS% %BUILDDIR%/texinfo + if errorlevel 1 exit /b 1 + echo. + echo.Build finished. The Texinfo files are in %BUILDDIR%/texinfo. + goto end +) + +if "%1" == "gettext" ( + %SPHINXBUILD% -b gettext %I18NSPHINXOPTS% %BUILDDIR%/locale + if errorlevel 1 exit /b 1 + echo. + echo.Build finished. The message catalogs are in %BUILDDIR%/locale. + goto end +) + +if "%1" == "changes" ( + %SPHINXBUILD% -b changes %ALLSPHINXOPTS% %BUILDDIR%/changes + if errorlevel 1 exit /b 1 + echo. + echo.The overview file is in %BUILDDIR%/changes. + goto end +) + +if "%1" == "linkcheck" ( + %SPHINXBUILD% -b linkcheck %ALLSPHINXOPTS% %BUILDDIR%/linkcheck + if errorlevel 1 exit /b 1 + echo. + echo.Link check complete; look for any errors in the above output ^ +or in %BUILDDIR%/linkcheck/output.txt. + goto end +) + +if "%1" == "doctest" ( + %SPHINXBUILD% -b doctest %ALLSPHINXOPTS% %BUILDDIR%/doctest + if errorlevel 1 exit /b 1 + echo. + echo.Testing of doctests in the sources finished, look at the ^ +results in %BUILDDIR%/doctest/output.txt. + goto end +) + +if "%1" == "xml" ( + %SPHINXBUILD% -b xml %ALLSPHINXOPTS% %BUILDDIR%/xml + if errorlevel 1 exit /b 1 + echo. + echo.Build finished. The XML files are in %BUILDDIR%/xml. + goto end +) + +if "%1" == "pseudoxml" ( + %SPHINXBUILD% -b pseudoxml %ALLSPHINXOPTS% %BUILDDIR%/pseudoxml + if errorlevel 1 exit /b 1 + echo. + echo.Build finished. The pseudo-XML files are in %BUILDDIR%/pseudoxml. + goto end +) + +:end diff --git a/docs/source/conf.py b/docs/source/conf.py new file mode 100644 index 0000000..035af2b --- /dev/null +++ b/docs/source/conf.py @@ -0,0 +1,272 @@ +#!/usr/bin/env python3 +# -*- coding: utf-8 -*- +# +# Segpy documentation build configuration file, created by +# sphinx-quickstart on Sat Jan 31 17:56:17 2015. +# +# This file is execfile()d with the current directory set to its +# containing dir. +# +# Note that not all possible configuration values are present in this +# autogenerated file. +# +# All configuration values have a default; values that are commented out +# serve to show the default. + +import sys + +# on_rtd is whether we are on readthedocs.org +import os +on_rtd = os.environ.get('READTHEDOCS', None) == 'True' + +# If extensions (or modules to document with autodoc) are in another directory, +# add these directories to sys.path here. If the directory is relative to the +# documentation root, use os.path.abspath to make it absolute, like shown here. +#sys.path.insert(0, os.path.abspath('.')) + +# -- General configuration ------------------------------------------------ + +# If your documentation needs a minimal Sphinx version, state it here. +#needs_sphinx = '1.0' + +# Add any Sphinx extension module names here, as strings. They can be +# extensions coming with Sphinx (named 'sphinx.ext.*') or your custom +# ones. +extensions = [ + 'sphinx.ext.autodoc', + 'sphinx.ext.todo', + 'sphinx.ext.ifconfig', +] + +# Add any paths that contain templates here, relative to this directory. +templates_path = ['_templates'] + +# The suffix of source filenames. +source_suffix = '.rst' + +# The encoding of source files. +#source_encoding = 'utf-8-sig' + +# The master toctree document. +master_doc = 'index' + +# General information about the project. +project = 'Segpy' +copyright = '2015, Robert Smallshire' + +# The version info for the project you're documenting, acts as replacement for +# |version| and |release|, also used in various other places throughout the +# built documents. +# +# The short X.Y version. +version = '2.0.0' +# The full version, including alpha/beta/rc tags. +release = '2.0.0' + +# The language for content autogenerated by Sphinx. Refer to documentation +# for a list of supported languages. +#language = None + +# There are two options for replacing |today|: either, you set today to some +# non-false value, then it is used: +#today = '' +# Else, today_fmt is used as the format for a strftime call. +#today_fmt = '%B %d, %Y' + +# List of patterns, relative to source directory, that match files and +# directories to ignore when looking for source files. +exclude_patterns = [] + +# The reST default role (used for this markup: `text`) to use for all +# documents. +#default_role = None + +# If true, '()' will be appended to :func: etc. cross-reference text. +#add_function_parentheses = True + +# If true, the current module name will be prepended to all description +# unit titles (such as .. function::). +#add_module_names = True + +# If true, sectionauthor and moduleauthor directives will be shown in the +# output. They are ignored by default. +#show_authors = False + +# The name of the Pygments (syntax highlighting) style to use. +pygments_style = 'sphinx' + +# A list of ignored prefixes for module index sorting. +#modindex_common_prefix = [] + +# If true, keep warnings as "system message" paragraphs in the built documents. +#keep_warnings = False + + +# -- Options for HTML output ---------------------------------------------- + +# The theme to use for HTML and HTML Help pages. See the documentation for +# a list of builtin themes. + +if not on_rtd: # only import and set the theme if we're building docs locally + import sphinx_rtd_theme + html_theme = 'sphinx_rtd_theme' + html_theme_path = [sphinx_rtd_theme.get_html_theme_path()] + +# otherwise, readthedocs.org uses their theme by default, so no need to specify it + +# Theme options are theme-specific and customize the look and feel of a theme +# further. For a list of options available for each theme, see the +# documentation. +#html_theme_options = {} + +# Add any paths that contain custom themes here, relative to this directory. +#html_theme_path = [] + +# The name for this set of Sphinx documents. If None, it defaults to +# " v documentation". +#html_title = None + +# A shorter title for the navigation bar. Default is the same as html_title. +#html_short_title = None + +# The name of an image file (relative to this directory) to place at the top +# of the sidebar. +#html_logo = None + +# The name of an image file (within the static path) to use as favicon of the +# docs. This file should be a Windows icon file (.ico) being 16x16 or 32x32 +# pixels large. +#html_favicon = None + +# Add any paths that contain custom static files (such as style sheets) here, +# relative to this directory. They are copied after the builtin static files, +# so a file named "default.css" will overwrite the builtin "default.css". +html_static_path = ['_static'] + +# Add any extra paths that contain custom files (such as robots.txt or +# .htaccess) here, relative to this directory. These files are copied +# directly to the root of the documentation. +#html_extra_path = [] + +# If not '', a 'Last updated on:' timestamp is inserted at every page bottom, +# using the given strftime format. +#html_last_updated_fmt = '%b %d, %Y' + +# If true, SmartyPants will be used to convert quotes and dashes to +# typographically correct entities. +#html_use_smartypants = True + +# Custom sidebar templates, maps document names to template names. +#html_sidebars = {} + +# Additional templates that should be rendered to pages, maps page names to +# template names. +#html_additional_pages = {} + +# If false, no module index is generated. +#html_domain_indices = True + +# If false, no index is generated. +#html_use_index = True + +# If true, the index is split into individual pages for each letter. +#html_split_index = False + +# If true, links to the reST sources are added to the pages. +#html_show_sourcelink = True + +# If true, "Created using Sphinx" is shown in the HTML footer. Default is True. +#html_show_sphinx = True + +# If true, "(C) Copyright ..." is shown in the HTML footer. Default is True. +#html_show_copyright = True + +# If true, an OpenSearch description file will be output, and all pages will +# contain a tag referring to it. The value of this option must be the +# base URL from which the finished HTML is served. +#html_use_opensearch = '' + +# This is the file name suffix for HTML files (e.g. ".xhtml"). +#html_file_suffix = None + +# Output file base name for HTML help builder. +htmlhelp_basename = 'Segpydoc' + + +# -- Options for LaTeX output --------------------------------------------- + +latex_elements = { +# The paper size ('letterpaper' or 'a4paper'). +#'papersize': 'letterpaper', + +# The font size ('10pt', '11pt' or '12pt'). +#'pointsize': '10pt', + +# Additional stuff for the LaTeX preamble. +#'preamble': '', +} + +# Grouping the document tree into LaTeX files. List of tuples +# (source start file, target name, title, +# author, documentclass [howto, manual, or own class]). +latex_documents = [ + ('index', 'Segpy.tex', 'Segpy Documentation', + 'Robert Smallshire', 'manual'), +] + +# The name of an image file (relative to this directory) to place at the top of +# the title page. +#latex_logo = None + +# For "manual" documents, if this is true, then toplevel headings are parts, +# not chapters. +#latex_use_parts = False + +# If true, show page references after internal links. +#latex_show_pagerefs = False + +# If true, show URL addresses after external links. +#latex_show_urls = False + +# Documents to append as an appendix to all manuals. +#latex_appendices = [] + +# If false, no module index is generated. +#latex_domain_indices = True + + +# -- Options for manual page output --------------------------------------- + +# One entry per manual page. List of tuples +# (source start file, name, description, authors, manual section). +man_pages = [ + ('index', 'segpy', 'Segpy Documentation', + ['Robert Smallshire'], 1) +] + +# If true, show URL addresses after external links. +#man_show_urls = False + + +# -- Options for Texinfo output ------------------------------------------- + +# Grouping the document tree into Texinfo files. List of tuples +# (source start file, target name, title, author, +# dir menu entry, description, category) +texinfo_documents = [ + ('index', 'Segpy', 'Segpy Documentation', + 'Robert Smallshire', 'Segpy', 'One line description of project.', + 'Miscellaneous'), +] + +# Documents to append as an appendix to all manuals. +#texinfo_appendices = [] + +# If false, no module index is generated. +#texinfo_domain_indices = True + +# How to display URL addresses: 'footnote', 'no', or 'inline'. +#texinfo_show_urls = 'footnote' + +# If true, do not generate a @detailmenu in the "Top" node's menu. +#texinfo_no_detailmenu = False diff --git a/docs/source/index.rst b/docs/source/index.rst new file mode 100644 index 0000000..4f1c544 --- /dev/null +++ b/docs/source/index.rst @@ -0,0 +1,49 @@ +.. Segpy documentation master file, created by + sphinx-quickstart on Sat Jan 31 17:56:17 2015. + You can adapt this file completely to your liking, but it should at least + contain the root `toctree` directive. + +===== +Segpy +===== + +*Segpy* is a Python package for reading and writing SEG Y data. The SEG Y file format is one of several standards +developed by the Society of Exploration Geophysicists for storing geophysical seismic data. It is an open standard, and +is controlled by the SEG Technical Standards Committee, a non-profit organization. + +This project aims to implement an open SEG Y module in Python for transporting seismic data between SEG Y files and +Python data structures. + +Contents +======== + +Front Matter +------------ + +.. toctree:: + :maxdepth: 2 + +Narrative Documentation +----------------------- + +Read this to learn how to use *Segpy*: + + +Reference Documentation +----------------------- + +Descriptions and examples for every public function, class and method in *Segpy*. + + +Change History +-------------- + + + +Indices and tables +================== + +* :ref:`genindex` +* :ref:`modindex` +* :ref:`search` + diff --git a/examples/loadsave.py b/examples/loadsave.py new file mode 100644 index 0000000..0b799f5 --- /dev/null +++ b/examples/loadsave.py @@ -0,0 +1,52 @@ +"""A simple example which loads a SEG Y file and saves it again. + +Usage: + + loadsave.py + +""" +from __future__ import print_function + +import os + +import sys +import traceback + +from segpy.reader import create_reader +from segpy.writer import write_segy + + +def load_save(in_filename, out_filename): + with open(in_filename, 'rb') as in_file, \ + open(out_filename, 'wb') as out_file: + + segy_reader = create_reader(in_file) + write_segy(out_file, segy_reader) + + +def main(argv=None): + if argv is None: + argv = sys.argv[1:] + + try: + in_filename = argv[0] + out_filename = argv[1] + except IndexError: + print(globals()['__doc__'], file=sys.stderr) + return os.EX_USAGE + + try: + load_save(in_filename, out_filename) + except (FileNotFoundError, IsADirectoryError) as e: + print(e, file=sys.stderr) + return os.EX_NOINPUT + except PermissionError as e: + print(e, file=sys.stderr) + return os.EX_NOPERM + except Exception as e: + traceback.print_exception(type(e), e, e.__traceback__, file=sys.stderr) + return os.EX_SOFTWARE + return os.EX_OK + +if __name__ == '__main__': + sys.exit(main()) diff --git a/examples/report.py b/examples/report.py new file mode 100644 index 0000000..bd827ab --- /dev/null +++ b/examples/report.py @@ -0,0 +1,81 @@ +"""Displays a simple report of a SEG Y file. + +Usage: + + report.py + +""" +from __future__ import print_function + +import os + +import sys +import traceback + +from segpy.reader import create_reader + + +def report_segy(in_filename): + with open(in_filename, 'rb') as in_file: + + segy_reader = create_reader(in_file) + print() + print("Filename: ", segy_reader.filename) + print("SEG Y revision: ", segy_reader.revision) + print("Number of traces: ", segy_reader.num_traces()) + print("Data format: ", + segy_reader.data_sample_format_description) + print("Dimensionality: ", segy_reader.dimensionality) + + try: + print("Number of CDPs: ", segy_reader.num_cdps()) + except AttributeError: + pass + + try: + print("Number of inlines: ", segy_reader.num_inlines()) + print("Number of crosslines: ", segy_reader.num_xlines()) + except AttributeError: + pass + + print("=== BEGIN TEXTUAL REEL HEADER ===") + for line in segy_reader.textual_reel_header: + print(line[3:]) + print("=== END TEXTUAL REEL HEADER ===") + print() + print("=== BEGIN EXTENDED TEXTUAL HEADER ===") + print(segy_reader.extended_textual_header) + print("=== END EXTENDED TEXTUAL_HEADER ===") + + for trace_index in segy_reader.trace_indexes(): + trace_header = segy_reader.trace_header(trace_index) + print("Inline {}, Crossline {}, Shotpoint {}".format(trace_header.Inline3D, trace_header.Crossline3D, + trace_header.ShotPoint)) + + +def main(argv=None): + if argv is None: + argv = sys.argv[1:] + + try: + in_filename = argv[0] + except IndexError: + print(globals()['__doc__'], file=sys.stderr) + return os.EX_USAGE + + try: + report_segy(in_filename) + except (FileNotFoundError, IsADirectoryError) as e: + print(e, file=sys.stderr) + return os.EX_NOINPUT + except PermissionError as e: + print(e, file=sys.stderr) + return os.EX_NOPERM + except Exception as e: + traceback.print_exception(type(e), e, e.__traceback__, file=sys.stderr) + return os.EX_SOFTWARE + return os.EX_OK + + +if __name__ == '__main__': + sys.exit(main()) \ No newline at end of file diff --git a/examples/timed_reader.py b/examples/timed_reader.py new file mode 100644 index 0000000..d4e78d9 --- /dev/null +++ b/examples/timed_reader.py @@ -0,0 +1,68 @@ +"""A simple example which times reading of all traces in a SEG Y file. + +Usage: + + timed_reader.py + +""" +from __future__ import print_function + +import datetime + +import os + +import sys +import traceback + +from segpy.reader import create_reader + + +def read_traces(in_filename): + with open(in_filename, 'rb') as in_file: + + t0 = datetime.datetime.now() + + segy_reader = create_reader(in_file) + + t1 = datetime.datetime.now() + + for trace_index in segy_reader.trace_indexes(): + trace = segy_reader.trace_samples(trace_index) + + t2 = datetime.datetime.now() + + time_to_read_header = (t1 - t0).total_seconds() + time_to_read_traces = (t2 - t1).total_seconds() + time_to_read_both = (t2 - t0).total_seconds() + + print("Time to read headers : {} seconds", time_to_read_header) + print("Time to read traces : {} seconds", time_to_read_traces) + print("Total time : {} seconds", time_to_read_both) + + +def main(argv=None): + if argv is None: + argv = sys.argv[1:] + + try: + in_filename = argv[0] + except IndexError: + print(globals()['__doc__'], file=sys.stderr) + return os.EX_USAGE + + try: + read_traces(in_filename) + except (FileNotFoundError, IsADirectoryError) as e: + print(e, file=sys.stderr) + return os.EX_NOINPUT + except PermissionError as e: + print(e, file=sys.stderr) + return os.EX_NOPERM + except Exception as e: + traceback.print_exception(type(e), e, e.__traceback__, file=sys.stderr) + return os.EX_SOFTWARE + return os.EX_OK + + +if __name__ == '__main__': + sys.exit(main()) diff --git a/examples/timeslice.py b/examples/timeslice.py new file mode 100644 index 0000000..7755c4f --- /dev/null +++ b/examples/timeslice.py @@ -0,0 +1,137 @@ +"""Extract a timeslice from a 3D seismic volume to a Numpy array. + +Usage: timeslice.py [-h] [--dtype DTYPE] [--null NULL] + segy-file npy-file slice-index + +Positional arguments: + segy-file Path to an existing SEG Y file of 3D seismic data + npy-file Path to the Numpy array file to be created for the timeslice + slice-index Zero based index of the time slice to be extracted + +Optional arguments: + -h, --help show this help message and exit + --dtype DTYPE Numpy data type. If not provided a dtype compatible with the + SEG Y data will be used. + --null NULL Sample value to use for missing or short traces. + +Example: + + timeslice.py stack_final_int8.sgy slice_800.npy 800 --null=42.0 --dtype=f +""" +from __future__ import print_function + +import argparse +import os +import sys +import traceback + +import numpy as np + +from segpy.reader import create_reader +from segpy_numpy.numpy.dtypes import make_dtype + + +class DimensionalityError(Exception): + pass + + +def extract_timeslice(segy_filename, out_filename, slice_index, dtype=None, null=0): + """Extract a timeslice from a 3D SEG Y file to a Numpy NPY file. + + Args: + segy_filename: Filename of a SEG Y file. + + out_filename: Filename of the NPY file. + + slice_index: The zero-based index (increasing with depth) of the slice to be extracted. + + dtype: Optional Numpy dtype for the result array. If not provided a dtype compatible with + the SEG Y data will be used. + + null: Optional sample value to use for missing or short traces. Defaults to zero. + """ + with open(segy_filename, 'rb') as segy_file: + + segy_reader = create_reader(segy_file) + + if dtype is None: + dtype = make_dtype(segy_reader.data_sample_format) + + if segy_reader.dimensionality != 3: + raise DimensionalityError("Cannot slice {n} dimensional seismic.".format(segy_reader.dimensionality)) + + i_line_range = segy_reader.inline_range() + x_line_range = segy_reader.xline_range() + + i_size = len(i_line_range) + x_size = len(x_line_range) + t_size = segy_reader.max_num_trace_samples() + + if not (0 <= slice_index < t_size): + raise ValueError("Time slice index {0} out of range {} to {}".format(slice_index, 0, t_size)) + + timeslice = np.full((x_size, i_size), null, dtype) + + for inline_num, xline_num in segy_reader.inline_xline_numbers(): + trace_index = segy_reader.trace_index((inline_num, xline_num)) + trace = segy_reader.trace_samples(trace_index) + + try: + sample = trace[slice_index] + except IndexError: + sample = null + + i_index = inline_num - i_line_range.start + x_index = xline_num - x_line_range.start + timeslice[x_index, i_index] = sample + + np.save(out_filename, timeslice) + + +def nullable_dtype(s): + return None if s == "" else np.dtype(s) + + +def main(argv=None): + parser = argparse.ArgumentParser() + parser.add_argument("segy_file", metavar="segy-file", + help="Path to an existing SEG Y file of 3D seismic data") + + parser.add_argument("npy_file", metavar="npy-file", + help="Path to the Numpy array file to be created for the timeslice") + + parser.add_argument("slice_index", metavar="slice-index", type=int, + help="Zero based index of the time slice to be extracted", ) + + parser.add_argument("--dtype", type=nullable_dtype, default="", + help="Numpy data type. If not provided a dtype compatible with the SEG Y data will be used.") + + parser.add_argument("--null", type=float, default=0.0, + help="Sample value to use for missing or short traces.") + + if argv is None: + argv = sys.argv[1:] + + args = parser.parse_args(argv) + + try: + extract_timeslice(args.segy_file, + args.npy_file, + args.slice_index, + args.dtype, + args.null) + except (FileNotFoundError, IsADirectoryError) as e: + print(e, file=sys.stderr) + return os.EX_NOINPUT + except PermissionError as e: + print(e, file=sys.stderr) + return os.EX_NOPERM + except Exception as e: + traceback.print_exception(type(e), e, e.__traceback__, file=sys.stderr) + return os.EX_SOFTWARE + return os.EX_OK + + +if __name__ == '__main__': + sys.exit(main()) + diff --git a/ibm_float.py b/ibm_float.py deleted file mode 100644 index 3fa7d7b..0000000 --- a/ibm_float.py +++ /dev/null @@ -1,22 +0,0 @@ -import struct - - -def ibm2ieee2(ibm_float): - """ - ibm2ieee2(ibm_float) - Used by permission - (C) Secchi Angelo - with thanks to Howard Lightstone and Anton Vredegoor. - """ - dividend = float(16 ** 6) - - if ibm_float == 0: - return 0.0 - istic, a, b, c = struct.unpack('>BBBB', ibm_float) - if istic >= 128: - sign = -1.0 - istic -= 128 - else: - sign = 1.0 - mant = float(a << 16) + float(b << 8) + float(c) - return sign * 16 ** (istic - 64) * (mant / dividend) diff --git a/makerelease.sh b/makerelease.sh deleted file mode 100755 index dcf37d9..0000000 --- a/makerelease.sh +++ /dev/null @@ -1,15 +0,0 @@ -#!/bin/sh -VERSION=0.3 - -DIR=segypy-$VERSION - -mkdir $DIR -cp segypy.py $DIR/. -cp testsegy.py $DIR/. -cp LICENSE $DIR/. -cp README $DIR/. - -zip -r $DIR.zip $DIR -tar cvfz $DIR.tgz $DIR - -rm -fr $DIR \ No newline at end of file diff --git a/plotting.py b/plotting.py deleted file mode 100644 index ba5b2bf..0000000 --- a/plotting.py +++ /dev/null @@ -1,34 +0,0 @@ -def image_segy(Data): - """ - imageSegy(Data) - Image segy Data - """ - import pylab - pylab.imshow(Data) - pylab.title('pymat test') - pylab.grid(True) - pylab.show() - - -def wiggle(Data, SH, skipt=1, maxval=8, lwidth=0.1): - """ - wiggle(Data, SH) - """ - import pylab - - t = range(SH['ns']) - - for i in range(0, SH['ntraces'], skipt): - - trace = Data[:, i] - trace[0] = 0 - trace[SH['ns'] - 1] = 0 - pylab.plot(i + trace / maxval, t, color='black', linewidth=lwidth) - for a in range(len(trace)): - if trace[a] < 0: - trace[a] = 0 - - pylab.fill(i + Data[:, i] / maxval, t, 'k', linewidth=0) - pylab.title(SH['filename']) - pylab.grid(True) - pylab.show() diff --git a/segpy-ext/segpy-numpy/DESCRIPTION.rst b/segpy-ext/segpy-numpy/DESCRIPTION.rst new file mode 100644 index 0000000..4b735c4 --- /dev/null +++ b/segpy-ext/segpy-numpy/DESCRIPTION.rst @@ -0,0 +1,20 @@ +Segpy-Numpy offers tools for working with both *Segpy* and *Numpy*. See the *Segpy* documentation for further details. + + +What It Does +============ + +How To Get It +============= + +*Segpy-Numpy* is available on the Python Package index and can be installed with ``pip``:: + + $ pip install segpy-numpy + + +Requirements +============ + +*Segpy-Numpy* should work with Python 3.2 and higher (and 2.7 for now). For the majority of use *Segpy 2* has no +externaldependencies. Optional modules with further dependencies such as *Numpy* are included in the ``segpy.ext`` +package of extras. diff --git a/segpy-ext/segpy-numpy/__init__.py b/segpy-ext/segpy-numpy/__init__.py new file mode 100644 index 0000000..8b13789 --- /dev/null +++ b/segpy-ext/segpy-numpy/__init__.py @@ -0,0 +1 @@ + diff --git a/segpy-ext/segpy-numpy/segpy_numpy/__init__.py b/segpy-ext/segpy-numpy/segpy_numpy/__init__.py new file mode 100644 index 0000000..420f4ca --- /dev/null +++ b/segpy-ext/segpy-numpy/segpy_numpy/__init__.py @@ -0,0 +1,10 @@ +print("segpy_numpy.__init__ imported") + +from pkgutil import extend_path + +#__path__ = extend_path(__path__, __name__) +__version__ = '2.0.0a1' + + +def load(): + pass diff --git a/segpy-ext/segpy-numpy/segpy_numpy/numpy/__init__.py b/segpy-ext/segpy-numpy/segpy_numpy/numpy/__init__.py new file mode 100644 index 0000000..8b13789 --- /dev/null +++ b/segpy-ext/segpy-numpy/segpy_numpy/numpy/__init__.py @@ -0,0 +1 @@ + diff --git a/segpy-ext/segpy-numpy/segpy_numpy/numpy/dtypes.py b/segpy-ext/segpy-numpy/segpy_numpy/numpy/dtypes.py new file mode 100644 index 0000000..2583caf --- /dev/null +++ b/segpy-ext/segpy-numpy/segpy_numpy/numpy/dtypes.py @@ -0,0 +1,32 @@ +"""Optional interoperability with Numpy.""" + +import numpy + +NUMPY_DTYPES = {'ibm': numpy.dtype('f4'), + 'int32': numpy.dtype('i4'), + 'int16': numpy.dtype('i2'), + 'float32': numpy.dtype('f4'), + 'int8': numpy.dtype('i1')} + + +def make_dtype(data_sample_format): + """Convert a SEG Y data sample format to a compatible numpy dtype. + + Note : + IBM float data sample formats ('ibm') will correspond to IEEE float data types. + + Args: + data_sample_format: A data sample format string. + + Returns: + A numpy.dtype instance. + + Raises: + ValueError: For unrecognised data sample format strings. + """ + try: + return NUMPY_DTYPES[data_sample_format] + except KeyError: + raise ValueError("Unknown data sample format string {!r}".format(data_sample_format)) + + diff --git a/segpy-ext/segpy-numpy/setup.cfg b/segpy-ext/segpy-numpy/setup.cfg new file mode 100644 index 0000000..79bc678 --- /dev/null +++ b/segpy-ext/segpy-numpy/setup.cfg @@ -0,0 +1,5 @@ +[bdist_wheel] +# This flag says that the code is written to work on both Python 2 and Python +# 3. If at all possible, it is good practice to do this. If you cannot, you +# will need to generate wheels for each Python version that you support. +universal=1 diff --git a/segpy-ext/segpy-numpy/setup.py b/segpy-ext/segpy-numpy/setup.py new file mode 100644 index 0000000..c604eaf --- /dev/null +++ b/segpy-ext/segpy-numpy/setup.py @@ -0,0 +1,127 @@ +import io +import os +import re +from setuptools import setup, find_packages # Always prefer setuptools over distutils +from codecs import open # To use a consistent encoding +from os import path + + +def read(*names, **kwargs): + with io.open( + os.path.join(os.path.dirname(__file__), *names), + encoding=kwargs.get("encoding", "utf8") + ) as fp: + return fp.read() + + +def find_version(*file_paths): + version_file = read(*file_paths) + version_match = re.search(r"^__version__ = ['\"]([^'\"]*)['\"]", + version_file, re.M) + if version_match: + return version_match.group(1) + raise RuntimeError("Unable to find version string.") + + +here = path.abspath(path.dirname(__file__)) + + +def local_file(name): + return os.path.join(here, name) + + + +# Get the long description from the relevant file +with open(local_file('DESCRIPTION.rst'), encoding='utf-8') as f: + long_description = f.read() + +setup( + name='segpy-numpy', + + # Versions should comply with PEP440. For a discussion on single-sourcing + # the version across setup.py and the project code, see + # https://packaging.python.org/en/latest/single_source_version.html + version=find_version("segpy_numpy/__init__.py"), + + description='Interoperability between Numpy with Segpy.', + long_description=long_description, + + # The project's main homepage. + url='https://github.com/rob-smallshire/segpy', + + # Author details + author='Robert Smallshire', + author_email='robert@smallshire.org.uk', + + # Choose your license + license='GPL', + + # See https://pypi.python.org/pypi?%3Aaction=list_classifiers + classifiers=[ + # How mature is this project? Common values are + # 3 - Alpha + # 4 - Beta + # 5 - Production/Stable + 'Development Status :: 3 - Alpha', + + # Indicate who your project is intended for + 'Intended Audience :: Developers', + 'Topic :: Scientific/Engineering', + 'Topic :: Software Development :: Libraries', + + # Pick your license as you wish (should match "license" above) + 'License :: OSI Approved :: MIT License', + + # Specify the Python versions you support here. In particular, ensure + # that you indicate whether you support Python 2, Python 3 or both. + 'Programming Language :: Python :: 2.7', + 'Programming Language :: Python :: 3', + 'Programming Language :: Python :: 3.3', + 'Programming Language :: Python :: 3.4', + ], + + # What does your project relate to? + keywords='seismic geocomputing geophysics numpy', + + # You can just specify the packages manually here if your project is + # simple. Or you can use find_packages(). + packages=find_packages(here, exclude=['segpy', 'contrib', 'docs', 'test*']), + + # List run-time dependencies here. These will be installed by pip when your + # project is installed. For an analysis of "install_requires" vs pip's + # requirements files see: + # https://packaging.python.org/en/latest/requirements.html + install_requires=['numpy'], + + # List additional groups of dependencies here (e.g. development dependencies). + # You can install these using the following syntax, for example: + # $ pip install -e .[dev,test] + extras_require = { + 'dev': ['check-manifest', 'wheel'], + 'doc': ['sphinx', 'cartouche'], + 'test': ['coverage', 'hypothesis'], + }, + + # If there are data files included in your packages that need to be + # installed, specify them here. If using Python 2.6 or less, then these + # have to be included in MANIFEST.in as well. + package_data={ + }, + + # Although 'package_data' is the preferred approach, in some case you may + # need to place data files outside of your packages. + # see http://docs.python.org/3.4/distutils/setupscript.html#installing-additional-files + # In this case, 'data_file' will be installed into '/my_data' + data_files=[], + + # To provide executable scripts, use entry points in preference to the + # "scripts" keyword. Entry points provide cross-platform support and allow + # pip to create the appropriate form of executable for the target platform. + + # Declare entry-points to modules. + entry_points={ + 'segpy.ext': 'segpy-numpy = segpy_numpy' + }, +) + + diff --git a/segpy/__init__.py b/segpy/__init__.py new file mode 100644 index 0000000..a790050 --- /dev/null +++ b/segpy/__init__.py @@ -0,0 +1 @@ +__version__ = '2.0.0a1' diff --git a/header_definition.py b/segpy/binary_reel_header_definition.py similarity index 95% rename from header_definition.py rename to segpy/binary_reel_header_definition.py index 46307cb..2979750 100644 --- a/header_definition.py +++ b/segpy/binary_reel_header_definition.py @@ -2,7 +2,7 @@ SEG Y Header Definition """ -from revisions import SEGY_REVISION_0, SEGY_REVISION_1 +from segpy.revisions import SEGY_REVISION_0, SEGY_REVISION_1 HEADER_DEF = {"Job": {"pos": 3200, "type": "int32", "def": 0}} HEADER_DEF["Line"] = {"pos": 3204, "type": "int32", "def": 0} @@ -47,13 +47,13 @@ HEADER_DEF["DataSampleFormat"]["datatype"][SEGY_REVISION_1] = { 1: 'ibm', 2: 'l', 3: 'h', - # 5: 'float', 5: 'f', 8: 'B'} HEADER_DEF["EnsembleFold"] = {"pos": 3226, "type": "int16", "def": 0} HEADER_DEF["TraceSorting"] = {"pos": 3228, "type": "int16", "def": 0} HEADER_DEF["VerticalSumCode"] = {"pos": 3230, "type": "int16", "def": 0} +HEADER_DEF["SweepFrequencyStart"] = {"pos": 3232, "type": "int16", "def": 0} HEADER_DEF["SweepFrequencyEnd"] = {"pos": 3234, "type": "int16", "def": 0} HEADER_DEF["SweepLength"] = {"pos": 3236, "type": "int16", "def": 0} HEADER_DEF["SweepType"] = {"pos": 3238, "type": "int16", "def": 0} diff --git a/segpy/caching.py b/segpy/caching.py new file mode 100644 index 0000000..ae95d6f --- /dev/null +++ b/segpy/caching.py @@ -0,0 +1,48 @@ +def lfu_cache(maxsize=100): + '''Least-frequently-used cache decorator. + + Arguments to the cached function must be hashable. + Cache performance statistics stored in f.hits and f.misses. + Clear the cache with f.clear(). + http://en.wikipedia.org/wiki/Least_Frequently_Used + + ''' + def decorating_function(user_function): + cache = {} # mapping of args to results + use_count = Counter() # times each key has been accessed + kwd_mark = object() # separate positional and keyword args + + @functools.wraps(user_function) + def wrapper(*args, **kwds): + key = args + if kwds: + key += (kwd_mark,) + tuple(sorted(kwds.items())) + use_count[key] += 1 + + # get cache entry or compute if not found + try: + result = cache[key] + wrapper.hits += 1 + except KeyError: + result = user_function(*args, **kwds) + cache[key] = result + wrapper.misses += 1 + + # purge least frequently used cache entry + if len(cache) > maxsize: + for key, _ in nsmallest(maxsize // 10, + use_count.iteritems(), + key=itemgetter(1)): + del cache[key], use_count[key] + + return result + + def clear(): + cache.clear() + use_count.clear() + wrapper.hits = wrapper.misses = 0 + + wrapper.hits = wrapper.misses = 0 + wrapper.clear = clear + return wrapper + return decorating_function diff --git a/segpy/catalog.py b/segpy/catalog.py new file mode 100644 index 0000000..663b5a3 --- /dev/null +++ b/segpy/catalog.py @@ -0,0 +1,588 @@ +from abc import abstractmethod, ABCMeta +from collections import Mapping, Sequence, OrderedDict +from fractions import Fraction + +from segpy.portability import reprlib +from segpy.util import contains_duplicates, measure_stride, minmax + + +class CatalogBuilder(object): + """Use a catalog builder to construct optimised, immutable mappings. + + A CatalogBuilder is useful when, depending on the particular keys and + values used, a more compact or efficient representation of the mapping + is possible than, say, a regular dictionary. The CatalogBuilder + accumulates values and then, once all values have been added, analyzes + the keys and values to produce a more optimized representation of the + mapping. + """ + + def __init__(self, mapping=None): + """Initialize a Catalog Builder. + + Args: + mapping: An optional mapping (such as a dictionary) of items. + """ + self._catalog = [] + if mapping is not None: + for key, value in mapping.items(): + self.add(key, value) + + def add(self, index, value): + """Add an item. + + Each index must be unique if create() is to be subsequently + called successfully, although duplicate index values will be + accepted by this call without complaint. + + """ + self._catalog.append((index, value)) + + def create(self): + """Create a possibly more optimized representation of the mapping. + + In this worst case, this method returns an object which is + essentially an immutable dictionary. In the best case, the + space savings can be vast. + + Returns: + A mapping, if a unique mapping from indexes to values is + possible, otherwise None. + + """ + + # This method examines the contents of the mapping using + # various heuristics to come up with a better representation. + + if len(self._catalog) < 2: + return DictionaryCatalog(self._catalog) + + # In-place sort by index + self._catalog.sort(key=lambda index_value: index_value[0]) + + if contains_duplicates(index for index, value in self._catalog): + return None + + if all(isinstance(index, Sequence) and (len(index) == 2) + for index, value in self._catalog): + return self._create_catalog_2() + + return self._create_catalog_1() + + def _create_catalog_1(self): + """Create a catalog for one-dimensional integer keys (i.e. scalars) + """ + index_min = self._catalog[0][0] + index_max = self._catalog[-1][0] + index_stride = measure_stride(index for index, value in self._catalog) + + if index_stride is None: + # Dictionary strategy - arbitrary keys and values + return DictionaryCatalog(self._catalog) + + self._catalog.sort(key=lambda index_value: index_value[1]) + value_min = self._catalog[0][1] + value_max = self._catalog[-1][1] + value_stride = measure_stride(value for index, value in self._catalog) + + if index_stride is not None and value_stride == 0: + assert value_min == value_max + return RegularConstantCatalog(index_min, + index_max, + index_stride, + value_min) + + if index_stride is None and value_stride == 0: + assert value_min == value_max + return ConstantCatalog( + (index for index, value in self._catalog), + value_min) + + if index_stride is not None and value_stride is None: + # Regular index - regular keys and arbitrary values + return RegularCatalog(index_min, + index_max, + index_stride, + (value for index, value in self._catalog)) + + assert (index_stride is not None) and (value_stride is not None) + catalog = LinearRegularCatalog(index_min, + index_max, + index_stride, + value_min, + value_max, + value_stride) + return catalog + + def _create_catalog_2(self): + """Create a catalog for two-dimensional integer keys. + + Each key must be a two-element sequence. + """ + i_min, i_max = minmax(i for (i, j), value in self._catalog) + j_min, j_max = minmax(j for (i, j), value in self._catalog) + + is_rm, diff = self._is_row_major(i_min, j_min, j_max) + if is_rm: + return RowMajorCatalog(i_min, i_max, j_min, j_max, diff) + return DictionaryCatalog(self._catalog) + + def _is_row_major(self, i_min, j_min, j_max): + """Does row major ordering predict values from keys? + + In row-major order the last dimension is contiguous, and so changes + quickest, when moving through the elements in storage order. Hence + the number of rows is the number of distinct i values and the numbers + of elements in each row (i.e. columns) is the number of distinct j. + + Args: + i_min: The minimum i value. + j_min: The minimum j value. + j_max: The maximum j value. + + Returns: + A 2-tuple containing, in the first element True if the values can + be predicted from the keys by assuming a row-major ordering, + otherwise False. If True, the second element will be a constant + offset, otherwise it can be ignored. + """ + diff = None + for (i, j), actual_value in self._catalog: + proposed_value = (i - i_min) * (j_max + 1 - j_min) + (j - j_min) + current_diff = actual_value - proposed_value + if diff is None: + diff = current_diff + if current_diff != diff: + return False, None + return True, diff + + +class Catalog(Mapping): + """An abstract base class for Catalogs which provides min and max keys and values.""" + __metaclass__ = ABCMeta + + @abstractmethod + def __init__(self, key_min=None, key_max=None, value_min=None, value_max=None): + """Must be overridden and called by subclasses. + + Args: + key_min: Optional minimum key. + key_max: Optional maximum key. + value_min: Optional minimum value. + value_max: Optional maximum value. + """ + self._min_key = key_min + self._max_key = key_max + self._min_value = value_min + self._max_value = value_max + + def key_min(self): + """Minimum key""" + if self._min_key is None: + self._min_key = min(self.keys()) + return self._min_key + + def key_max(self): + """Maximum key""" + if self._max_key is None: + self._max_key = max(self.keys()) + return self._max_key + + def value_min(self): + """Minimum value""" + if self._min_value is None: + self._min_value = min(self.values()) + return self._min_value + + def value_max(self): + """Maximum value""" + if self._max_value is None: + self._max_value = max(self.values()) + return self._max_value + + +class RowMajorCatalog(Catalog): + """A mapping which assumes a row-major ordering of a two-dimensional matrix. + + This is the ordering of items in a two-dimensional matrix where in + the (i, j) key tuple the j value changes fastest when iterating + through the items in order. + + A RowMajorCatalog predicts the value v from the key (i, j) according to the + following formula: + + v = (i - i_min) * j_max + (j - j_min) + c + + for + i_min <= i <= i_max + j_min <= j <= j_max + + and where c is an integer constant to allow zero- or one-based indexing. + """ + + def __init__(self, i_min, i_max, j_min, j_max, c): + """Initialize a RowMajorCatalog. + + Args: + i_min (int): The minimum i value. + i_max (int): The maximum i value. + j_min (int): The minimum j value. + j_max (int): The maximum j value. + c (int): The constant offset + """ + super(RowMajorCatalog, self).__init__() + self._i_min = i_min + self._i_max = i_max + self._j_min = j_min + self._j_max = j_max + self._c = c + + @property + def i_min(self): + """Minimum i value""" + return self._i_min + + @property + def i_max(self): + """Maximum i value""" + return self._i_max + + @property + def j_min(self): + """Minimum j value""" + return self._j_min + + @property + def j_max(self): + """Maximum j value""" + return self._j_max + + def key_min(self): + """Minimum (i, j) key""" + return self._i_min, self._j_min + + def key_max(self): + """Maximum (i, j) key""" + return self._i_max, self._j_max + + def value_min(self): + """Minimum value at key_min""" + return self[self.key_min()] + + def value_max(self): + """Maximum value at key_max""" + return self[self.key_max()] + + def __getitem__(self, key): + i, j = key + if not (self._i_min <= i <= self._i_max) and \ + (self._j_min <= j <= self._j_max): + raise KeyError("{!r} key {!r} out of range".format(self, key)) + value = (i - self._i_min) * (self._j_max + 1 - self._j_min) + (j - self._j_min) + self._c + return value + + def __contains__(self, key): + i, j = key + return (self._i_min <= i <= self._i_max) and \ + (self._j_min <= j <= self._j_max) + + def __len__(self): + return (self._i_max - self._i_min) * (self._j_max + 1 - self._j_min) + + def __iter__(self): + for i in range(self._i_min, self._i_max + 1): + for j in range(self._j_min, self._j_max + 1): + yield (i, j) + + def __repr__(self): + return '{}({}, {}, {}, {}, {})'.format( + self.__class__.__name__, + self._i_min, self._i_max, self._j_min, self._j_max, self._c) + + +class DictionaryCatalog(Catalog): + """An immutable, ordered, dictionary mapping. + """ + + def __init__(self, items): + super(DictionaryCatalog, self).__init__() + self._items = OrderedDict(items) + + def __getitem__(self, key): + return self._items[key] + + def __iter__(self): + return iter(self._items) + + def __len__(self): + return len(self._items) + + def __contains__(self, item): + return item in self._items + + def __repr__(self): + return '{}({})'.format( + self.__class__.__name__, reprlib.repr(self._items.items())) + + +class RegularConstantCatalog(Catalog): + """Mapping with keys ordered with regular spacing along the number line. + + The values associated with the keys are constant. + """ + + def __init__(self, key_min, key_max, key_stride, value): + """Initialize a RegularConstantCatalog. + + The catalog is initialized by a description of how the keys + are distributed along the number line, and a value which + corresponds with all keys. + + Args: + key_min: The minimum key. + key_max: The maximum key. + key_stride: The difference between successive keys. + value: A value associated with all keys. + """ + key_range = key_max - key_min + if key_range % key_stride != 0: + raise ValueError("RegularIndex key range {!r} is not " + "a multiple of stride {!r}".format( + key_stride, key_range)) + super(RegularConstantCatalog, self).__init__( + key_min=key_min, + key_max=key_max, + value_min=value, + value_max=value) + self._key_stride = key_stride + + def __getitem__(self, key): + if key not in self: + raise KeyError("{!r} does not contain key {!r}".format(self, key)) + return self.value_min() + + def __len__(self): + return 1 + (self.key_max() - self.key_min()) / self._key_stride + + def __contains__(self, key): + return (self.key_min() <= key <= self.key_max()) and \ + ((key - self.key_min()) % self._key_stride == 0) + + def __iter__(self): + return iter(range(self.key_min(), + self.key_max() + 1, + self._key_stride)) + + def __repr__(self): + return '{}({}, {}, {}, {})'.format( + self.__class__.__name__, + self.key_min(), + self.key_max(), + self._key_stride, + self.value_min()) + + +class ConstantCatalog(Catalog): + """Mapping with arbitrary keys and a single constant value. + """ + + def __init__(self, keys, value): + """Initialize a RegularConstantCatalog. + + The catalog is initialized by a description with an iterable series of + keys and a constant value to be associated with all the keys. + + Args: + keys: An iterable series of distinct keys. + key_max: The maximum key. + key_stride: The difference between successive keys. + value: A value associated with all keys. + """ + super(ConstantCatalog, self).__init__(value_min=value, value_max=value) + self._items = frozenset(keys) + + def __getitem__(self, key): + if key not in self: + raise KeyError("{!r} does not contain key {!r}".format(self, key)) + return self.value_min() + + def __len__(self): + return len(self._items) + + def __contains__(self, key): + return key in self._items + + def __iter__(self): + return iter(self._items) + + def __repr__(self): + return '{}({}, {})'.format( + self.__class__.__name__, + reprlib.repr(self._items), + self.value_min()) + + +class RegularCatalog(Catalog): + """Mapping with keys ordered with regular spacing along the number line. + + The values associated with the keys are arbitrary. + """ + + def __init__(self, key_min, key_max, key_stride, values): + """Initialize a RegularCatalog. + + The catalog is initialized by a description of how the keys + are distributed along the number line, and an iterable series of + corresponding values. + + Args: + key_min: The minimum key. + key_max: The maximum key. + key_stride: The difference between successive keys. + values: An iterable series of values corresponding to the keys. + + Raises: + ValueError: There is any inconsistency in the keys, stride, + and/or values. + """ + key_range = key_max - key_min + if key_range % key_stride != 0: + raise ValueError("{} key range {!r} is not " + "a multiple of stride {!r}".format(self.__class__.__name__, + key_stride, key_range)) + super(RegularCatalog, self).__init__(key_min=key_min, key_max=key_max) + self._key_stride = key_stride + self._values = list(values) + num_keys = key_range // key_stride + if num_keys != len(self._values): + raise ValueError("{} key range and values inconsistent".format(self.__class__.__name__)) + + def __getitem__(self, key): + if not (self.key_min() <= key <= self.key_max()): + raise KeyError("{!r} key {!r} out of range".format(self, key)) + offset = key - self.key_min() + if offset % self._key_stride != 0: + raise KeyError("{!r} does not contain key {!r}".format(self, key)) + index = offset // self._key_stride + return self._values[index] + + def __len__(self): + return len(self._values) + + def __contains__(self, key): + return (self.key_min() <= key <= self.key_max()) and \ + ((key - self.key_min()) % self._key_stride == 0) + + def __iter__(self): + return iter(range(self.key_min(), + self.key_max() + 1, + self._key_stride)) + + def __repr__(self): + return '{}({}, {}, {}, {})'.format( + self.__class__.__name__, + self.key_min(), + self.key_max(), + self._key_stride, + reprlib.repr(self._values)) + + +class LinearRegularCatalog(Catalog): + """A mapping which assumes a linear relationship between keys and values. + + This is the ordering of items in a two-dimensional matrix where in + the (i, j) key tuple the j value changes fastest when iterating + through the items in order. + + A LinearRegularCatalog predicts the value v from the key according to the + following formula: + + v = (value_max - value_min) / (key_max - key_min) * (key - key_min) + value_min + """ + + def __init__(self, + key_min, + key_max, + key_stride, + value_min, + value_max, + value_stride): + """Initialize a LinearRegularCatalog. + + Args: + key_min: The minimum key. + key_max: The maximum key. + key_stride: The difference between successive keys. + value_min: The minimum value. + value_max: The maximum value. + + Raises: + ValueError: There is any inconsistency in the keys, strides, + and/or values. + """ + key_range = key_max - key_min + if key_range % key_stride != 0: + raise ValueError("{} key range {!r} is not " + "a multiple of key stride {!r}".format( + self.__class__.__name__, + key_stride, + key_range)) + self._key_stride = key_stride + + value_range = value_max - value_min + if value_range % value_stride != 0: + raise ValueError("{} value range {!r} is not " + "a multiple of value stride {!r}".format( + self.__class__.__name__, + value_stride, + value_range)) + self._value_stride = value_stride + + super(LinearRegularCatalog, self).__init__( + key_min=key_min, + key_max=key_max, + value_min=value_min, + value_max=value_max) + + num_keys = (self.key_max() - self.key_min()) // self._key_stride + num_values = (self.value_max() - self.value_min()) // self._value_stride + if num_keys != num_values: + raise ValueError("{} inconsistent number of " + "keys {} and values {}".format( + self.__class__.__name__, + num_keys, + num_values)) + + self._m = Fraction(self.value_max() - self.value_min(), + self.key_max() - self.key_min()) + + def __getitem__(self, key): + if not (self.key_min() <= key <= self.key_max()): + raise KeyError("{!r} key {!r} out of range".format(self, key)) + offset = key - self.key_min() + if offset % self._key_stride != 0: + raise KeyError("{!r} does not contain key {!r}".format(self, key)) + + v = self._m * (key - self.key_min()) + self.value_min() + assert v.denominator == 1 + return v.numerator + + def __len__(self): + return 1 + (self.key_max() - self.key_min()) // self._key_stride + + def __contains__(self, key): + return (self.key_min() <= key <= self.key_max()) and \ + ((key - self.key_min()) % self._key_stride == 0) + + def __iter__(self): + return iter(range(self.key_min(), self.key_max() + 1, self._key_stride)) + + def __repr__(self): + return '{}({}, {}, {}, {}, {}, {})'.format( + self.__class__.__name__, + self.key_min(), + self.key_max(), + self._key_stride, + self.value_min(), + self.value_max(), + self._value_stride) diff --git a/segpy/datatypes.py b/segpy/datatypes.py new file mode 100644 index 0000000..0ffbc1f --- /dev/null +++ b/segpy/datatypes.py @@ -0,0 +1,39 @@ +DATA_SAMPLE_FORMAT = {1: 'ibm', + 2: 'int32', + 3: 'int16', + 5: 'float32', + 8: 'int8'} + +# A mapping from SEG Y data types to format characters used by the struct module +CTYPES = {'int32': 'i', + 'uint32': 'I', + 'int16': 'h', + 'uint16': 'H', + 'int8': 'b', + 'uint8': 'B', + 'float32': 'f', + 'ibm': 'ibm'} + + +CTYPE_DESCRIPTION = {'ibm': 'IBM float', + 'int32': '32 bit signed integer', + 'uint32': '32 bit unsigned integer', + 'int16': '16 bit signed integer', + 'uint16': '16 bit unsigned integer', + 'float32': 'IEEE float32', + 'int8': '8 bit signed integer (byte)', + 'uint8': '8 bit unsigned integer (byte)'} + + +SIZES = dict(i=4, + I=4, + h=2, + H=2, + b=1, + B=1, + f=4, + ibm=4) + + +def size_in_bytes(ctype): + return SIZES[ctype] diff --git a/segpy/encoding.py b/segpy/encoding.py new file mode 100644 index 0000000..149230e --- /dev/null +++ b/segpy/encoding.py @@ -0,0 +1,78 @@ +ASCII = 'ascii' +EBCDIC = 'cp037' + +SUPPORTED_ENCODINGS = (ASCII, EBCDIC) + + +class UnsupportedEncodingError(Exception): + + def __init__(self, text, encoding): + self._encoding = encoding + super(UnsupportedEncodingError, self).__init__(text) + + @property + def encoding(self): + return self._encoding + + def __str__(self): + return "{} not supported for encoding {}".format(self.args[0], self._encoding) + + def __repr__(self): + return "{}({!r}, {!r}".format(self.__class__.__name__, self.args[0], self._encoding) + + +def is_supported_encoding(encoding): + return encoding in SUPPORTED_ENCODINGS + + +COMMON_CHARS = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789:_- ' +COMMON_EBCDIC_CHARS = set(COMMON_CHARS.encode(EBCDIC)) +COMMON_ASCII_CHARS = set(COMMON_CHARS.encode(ASCII)) + +def guess_encoding(bs, threshold=0.5): + """Try to determine whether the encoding of byte stream b is an ASCII string or an EBCDIC string. + + Args: + bs: A byte string (Python 2 - str; Python 3 - bytes) + + Returns: + A string which can be used with the Python encoding functions: 'cp037' for EBCDIC, 'ascii' for ASCII or None + if neither. + """ + + ebcdic_count = 0 + ascii_count = 0 + null_count = 0 + + count = 0 + for b in bs: + if b in COMMON_EBCDIC_CHARS: + ebcdic_count +=1 + if b in COMMON_ASCII_CHARS: + ascii_count +=1 + if b == 0: + null_count += 1 + count += 1 + + if count == 0: + return None + + ebcdic_freq = ebcdic_count / count + ascii_freq = ascii_count / count + null_freq = null_count / count + + if null_freq == 1.0: + return ASCII # Doesn't matter + + if ebcdic_freq < threshold and ascii_freq >= threshold: + return ASCII + + if ebcdic_freq >= threshold and ascii_freq < threshold: + return EBCDIC + + if ebcdic_freq < threshold and ascii_freq < threshold: + return None + + + + return None diff --git a/segpy/ext/__init__.py b/segpy/ext/__init__.py new file mode 100644 index 0000000..ba891c3 --- /dev/null +++ b/segpy/ext/__init__.py @@ -0,0 +1,20 @@ +import pkg_resources + +loaded = set() + + +def load_entry_points(name=None): + """Load extension packages into the segpy.ext namespace. + + Any packages registered against the 'segpy.ext' entry-point group will be + installed dynamically into the segpy.ext namespace. + """ + for entry_point in pkg_resources.iter_entry_points(group='segpy.ext', name=name): + package = entry_point.load() + if package not in loaded: + loaded.add(package) + __path__.extend(package.__path__) + package.load() + + +load_entry_points() diff --git a/segpy/ibm_float.py b/segpy/ibm_float.py new file mode 100644 index 0000000..076867e --- /dev/null +++ b/segpy/ibm_float.py @@ -0,0 +1,491 @@ +from math import frexp, isnan, isinf, ceil, floor, trunc +from numbers import Real + +from segpy.portability import long_int, byte_string, four_bytes + + + +IBM_ZERO_BYTES = b'\x00\x00\x00\x00' +IBM_NEGATIVE_ONE_BYTES = b'\xc1\x10\x00\x00' +IBM_POSITIVE_ONE_BYTES = b'A\x10\x00\x00' + +MIN_IBM_FLOAT = -7.2370051459731155e+75 +LARGEST_NEGATIVE_NORMAL_IBM_FLOAT = -5.397605346934028e-79 +SMALLEST_POSITIVE_NORMAL_IBM_FLOAT = 5.397605346934028e-79 +MAX_IBM_FLOAT = 7.2370051459731155e+75 + +MAX_BITS_PRECISION_IBM_FLOAT = 24 +MIN_BITS_PRECISION_IBM_FLOAT = 21 # The first 3 bits of the mantissa may be zero +EPSILON_IBM_FLOAT = pow(2.0, -(MIN_BITS_PRECISION_IBM_FLOAT - 1)) +_L24 = long_int(2) ** MAX_BITS_PRECISION_IBM_FLOAT +_F24 = float(pow(2, MAX_BITS_PRECISION_IBM_FLOAT)) + +_L21 = long_int(2) ** MIN_BITS_PRECISION_IBM_FLOAT + +EXPONENT_BIAS = 64 + +MIN_EXACT_INTEGER_IBM_FLOAT = -2**MAX_BITS_PRECISION_IBM_FLOAT +MAX_EXACT_INTEGER_IBM_FLOAT = 2**MIN_BITS_PRECISION_IBM_FLOAT + + +def ibm2ieee(big_endian_bytes): + """Interpret a byte string as a big-endian IBM float. + + Args: + big_endian_bytes (str): A string containing at least four bytes. + + Returns: + The floating point value. + """ + a, b, c, d = four_bytes(big_endian_bytes) + + if a == b == c == d == 0: + return 0.0 + + sign = -1 if (a & 0x80) else 1 + exponent_16_biased = a & 0x7f + mantissa = ((b << 16) | (c << 8) | d) / _F24 + + value = sign * mantissa * pow(16, exponent_16_biased - EXPONENT_BIAS) + return value + +BITS_PER_NYBBLE = 4 + + +def truncate(big_endian_bytes): + a, b, c, d = four_bytes(big_endian_bytes) + + sign = -1 if (a & 0x80) else 1 + exponent_16_biased = a & 0x7f + exponent_16 = exponent_16_biased - EXPONENT_BIAS + mantissa = ((b << 16) | (c << 8) | d) + + print("sign =", sign) + print("exponent_16", exponent_16, hex(exponent_16), bin(exponent_16)) + print("mantissa", mantissa, hex(mantissa), bin(mantissa)) + + num_nybbles_to_preserve = min(exponent_16, MAX_BITS_PRECISION_IBM_FLOAT // BITS_PER_NYBBLE) + num_bits_to_clear = MAX_BITS_PRECISION_IBM_FLOAT - num_nybbles_to_preserve * BITS_PER_NYBBLE + clear_mask = 2**num_bits_to_clear - 1 + preserve_mask = (2**MAX_BITS_PRECISION_IBM_FLOAT - 1) & ~clear_mask + + print("num_nybbles_to_preserve", num_nybbles_to_preserve) + print("num_bits_to_clear", num_bits_to_clear) + print("clear_mask ", bin(clear_mask)) + print("preserve_mask", bin(preserve_mask)) + + truncated_mantissa = mantissa & preserve_mask + + value = truncated_mantissa * pow(16, exponent_16) + + scaled_value = value >> MAX_BITS_PRECISION_IBM_FLOAT + + return scaled_value + + # + # tb = (preserve_mask >> 16) & b + # tc = (preserve_mask >> 8) & c + # td = preserve_mask & d + # + # return byte_string((a, tb, tc, td)) + + +def ieee2ibm(f): + """Convert a float to four big-endian bytes representing an IBM float. + + Args: + f (float): The value to be converted. + + Returns: + A bytes object (Python 3) or a string (Python 2) containing four + bytes representing a big-endian IBM float. + + Raises: + OverflowError: If f is outside the representable range. + ValueError: If f is NaN or infinite. + FloatingPointError: If f cannot be represented without total loss of precision. + """ + if f == 0: + # There are many potential representations of zero - this is the standard one + return b'\x00\x00\x00\x00' + + if isnan(f): + raise ValueError("NaN cannot be represented in IBM floating point") + + if isinf(f): + raise ValueError("Infinities cannot be represented in IBM floating point") + + if f < MIN_IBM_FLOAT: + raise OverflowError("IEEE Floating point value {} is less than the " + "representable minimum for IBM floats.".format(f)) + + if f > MAX_IBM_FLOAT: + raise OverflowError("IEEE Floating point value {} is greater than the " + "representable maximum for IBM floats".format(f)) + + # Now compute m and e to satisfy: + # + # f = m * 2^e + # + # where 0.5 <= abs(m) < 1 + # except when f == 0 in which case m == 0 and e == 0, which we've already + # dealt with. + m, e = frexp(f) + + # Convert the fraction (m) into an integer representation. IEEE float32 + # numbers have 23 explicit (24 implicit) bits of precision. + + mantissa = abs(long_int(m * _L24)) + exponent = e + sign = 0x80 if f < 0 else 0x00 + + # IBM single precision floats are of the form + # (-1)^sign * 0.significand * 16^(exponent-64) + + # Adjust the exponent, and the mantissa in sympathy so it is + # a multiple of four, so it can be expressed in base 16 + remainder = exponent % 4 + if remainder != 0: + shift = 4 - remainder + mantissa >>= shift + exponent += shift + + exponent_16 = exponent >> 2 # Divide by four to convert to base 16 + exponent_16_biased = exponent_16 + 64 # Add the exponent bias of 64 + + # If the biased exponent is negative, we try to use a subnormal representation + if exponent_16_biased < 0: + shift_16 = 0 - exponent_16_biased + exponent_16_biased += shift_16 # An increment of the base-16 exponent must be balanced by + mantissa >>= 4 * shift_16 # A division by 16 (four binary places) in the mantissa + if mantissa == 0: + raise FloatingPointError("IEEE Floating point value {} is smaller than the " + "smallest subnormal number for IBM floats.".format(f)) + + a = sign | exponent_16_biased + b = (mantissa >> 16) & 0xff + c = (mantissa >> 8) & 0xff + d = mantissa & 0xff + + return byte_string((a, b, c, d)) + + +class IBMFloat(Real): + + __slots__ = ['_data'] + + _INTERNED = {IBM_ZERO_BYTES: None, + IBM_NEGATIVE_ONE_BYTES: None, + IBM_POSITIVE_ONE_BYTES: None} + + # noinspection PyUnresolvedReferences + def __new__(cls, b): + obj = object.__new__(cls) + + data = bytes(b) + num_bytes = len(data) + if num_bytes != 4: + raise ValueError("{} cannot be constructed from {} values".format(cls.__name__, num_bytes)) + obj._data = data + + # Intern common values + if data in cls._INTERNED: + if cls._INTERNED[data] is None: + cls._INTERNED[data] = obj + return cls._INTERNED[data] + + return obj + + + @classmethod + def from_float(cls, f): + """Construct an IBMFloat from an IEEE float. + + Args: + f (float): The value to be converted. + + Returns: + An IBMFloat. + + Raises: + OverflowError: If f is outside the representable range. + ValueError: If f is NaN or infinite. + FloatingPointError: If f cannot be represented without total loss of precision. + """ + return cls(ieee2ibm(f)) + + @classmethod + def from_real(cls, f): + if isinstance(f, IBMFloat): + return f + return cls.from_float(f) + + @classmethod + def from_bytes(cls, b): + return cls(b) + + @classmethod + def ldexp(cls, fraction, exponent): + """Make an IBMFloat from fraction and exponent. + + The is the inverse function of IBMFloat.frexp() + + Args: + fraction: A Real in the range -1.0 to 1.0. + exponent: An integer in the range -256 to 255 inclusive. + """ + if not (-1.0 <= fraction <= 1.0): + raise ValueError("ldexp fraction {!r} out of range -1.0 to +1.0") + + if not (-256 <= exponent < 256): + raise ValueError("ldexp exponent {!r} out of range -256 to 256") + + ieee = fraction * 2**exponent + return IBMFloat.from_float(ieee) + + @property + def signbit(self): + """True if the value is negative, otherwise False.""" + return bool(self._data[0] & 0x80) + + def __float__(self): + return ibm2ieee(self._data) + + def __bytes__(self): + return self._data + + def __repr__(self): + return "{}.from_float({!r}) ~{!r}".format(self.__class__.__name__, self._data, float(self)) + + def __str__(self): + return str(float(self)) + + def __bool__(self): + return not self.is_zero() + + def is_zero(self): + return self.int_mantissa == 0 + + def __nonzero__(self): + return not self.is_zero() + + def is_subnormal(self): + if self.is_zero(): + # Only one of the many possible representations of zero is considered 'normal' - all the zeros + return not all(b == 0 for b in self._data) + + return self._data[1] < 16 # TODO: Replace magic number with constant + + def zero_subnormal(self): + return IBM_FLOAT_ZERO if self.is_subnormal() else self + + def frexp(self): + """Obtain the fraction and exponent. + + Returns: + A pair where the first item is the fraction in the range -1.0 and +1.0 and the + exponent is an integer such that f = fraction * 2**exponent + """ + sign = -1 if self.signbit else 1 + mantissa = sign * self.int_mantissa / _F24 + exp_2 = self.exp16 * 4 + return mantissa, exp_2 + + def __pos__(self): + return self + + def __neg__(self): + if self.is_zero(): + return IBM_FLOAT_ZERO + + data = self._data + return IBMFloat((data[0] ^ 0b10000000, + data[1], + data[2], + data[3])) + + def __abs__(self): + if self.is_zero(): + return IBM_FLOAT_ZERO + + data = self._data + return IBMFloat((data[0] & 0b01111111, + data[1], + data[2], + data[3])) + + def __eq__(self, rhs): + lhs = self + + if not isinstance(rhs, IBMFloat): + return float(lhs) == float(rhs) + + lhs_sign = lhs.signbit + rhs_sign = rhs.signbit + + if lhs_sign != rhs_sign: + return False + + nlhs = lhs.normalize() + nrhs = rhs.normalize() + + if not (nlhs.is_subnormal() or nrhs.is_subnormal()): + # Both of the numbers are normalised + return nlhs._data == nrhs._data + + # Either or both of the numbers are subnormal + lhs_exp16 = nlhs.exp16 + rhs_exp16 = nrhs.exp16 + + lhs_mantissa = nlhs.int_mantissa + rhs_mantissa = nrhs.int_mantissa + + if lhs_exp16 < rhs_exp16: + delta_exp16 = rhs_exp16 - lhs_exp16 + lhs_mantissa >>= 4 * delta_exp16 + lhs_exp16 += delta_exp16 + + if lhs_exp16 > rhs_exp16: + delta_exp16 = lhs_exp16 - rhs_exp16 + rhs_mantissa >>= 4 * delta_exp16 + rhs_exp16 += delta_exp16 + + assert lhs_exp16 == rhs_exp16 + return lhs_mantissa == rhs_mantissa + + def __floordiv__(self, rhs): + return float(self) // float(rhs) + + def __rfloordiv__(self, lhs): + return float(lhs) // float(self) + + def __rtruediv__(self, lhs): + q = float(lhs) / float(self) + return IBMFloat.from_float(q) if isinstance(lhs, float) else q + + def __pow__(self, exponent): + p = pow(float(self), float(exponent)) + return IBMFloat.from_float(p) if isinstance(exponent, IBMFloat) else p + + def __rpow__(self, base): + return IBMFloat.from_float(pow(float(base), float(self))) + + def __mod__(self, rhs): + m = float(self) % float(rhs) + return IBMFloat.from_float(m) if isinstance(rhs, IBMFloat) else m + + def __rmod__(self, lhs): + m = float(lhs) % float(self) + return IBMFloat.from_float(m) if isinstance(lhs, IBMFloat) else m + + def __rmul__(self, lhs): + p = float(lhs) * float(self) + return IBMFloat.from_float(p) if isinstance(lhs, IBMFloat) else p + + def __radd__(self, lhs): + s = float(lhs) + float(self) + return IBMFloat.from_float(s) if isinstance(lhs, IBMFloat) else s + + def __lt__(self, rhs): + return float(self) < float(rhs) + + def __le__(self, rhs): + return float(self) <= float(rhs) + + def __gt__(self, rhs): + return float(self) > float(rhs) + + def __ge__(self, rhs): + return float(self) >= float(rhs) + + def __ceil__(self): + t = trunc(self) + return t if self.signbit else t + 1 + + def __floor__(self): + t = trunc(self) + return t - 1 if self.signbit else t + + @property + def exp16(self): + """The base 16 exponent.""" + exponent_16_biased = self._data[0] & 0x7f + exponent_16 = exponent_16_biased - EXPONENT_BIAS + return exponent_16 + + @property + def int_mantissa(self): + data = self._data + return (data[1] << 16) | (data[2] << 8) | data[3] + + def __trunc__(self): + sign = -1 if self.signbit else 1 + exponent_16 = self.exp16 + mantissa = self.int_mantissa + + num_nybbles_to_preserve = min(exponent_16, MAX_BITS_PRECISION_IBM_FLOAT // BITS_PER_NYBBLE) + num_bits_to_clear = MAX_BITS_PRECISION_IBM_FLOAT - num_nybbles_to_preserve * BITS_PER_NYBBLE + clear_mask = 2**num_bits_to_clear - 1 + preserve_mask = (2**MAX_BITS_PRECISION_IBM_FLOAT - 1) & ~clear_mask + + truncated_mantissa = mantissa & preserve_mask + magnitude = truncated_mantissa * pow(16, exponent_16) >> MAX_BITS_PRECISION_IBM_FLOAT + return sign * magnitude + + def normalize(self): + """Normalize the floating point value. + + Returns: + A normalized IBMFloat equal in value to this object. + + Raises: + FloatingPointError: If the number could not be normalized. + """ + if self.is_zero(): + return IBM_FLOAT_ZERO + + exponent_16 = self.exp16 + mantissa = self.int_mantissa + + while mantissa < (1 << 20): + new_exponent_16 = exponent_16 - 1 + if not (-64 <= new_exponent_16 < 64): + raise FloatingPointError("Could not normalize {!r} without causing exponent overflow.".format(self)) + + mantissa <<= 4 + exponent_16 = new_exponent_16 + + exponent_16_biased = exponent_16 + EXPONENT_BIAS + + sign = int(self.signbit) << 7 + + a = sign | exponent_16_biased + b = (mantissa >> 16) & 0xff + c = (mantissa >> 8) & 0xff + d = mantissa & 0xff + + return IBMFloat.from_bytes((a, b, c, d)) + + def __round__(self, ndigits=None): + return IBMFloat.from_float(round(float(self), ndigits)) + + def __truediv__(self, rhs): + q = float(self) / float(rhs) + return IBMFloat.from_float(q) if isinstance(rhs, IBMFloat) else q + + def __mul__(self, rhs): + p = float(self) * float(rhs) + return IBMFloat.from_float(p) if isinstance(rhs, IBMFloat) else p + + def __add__(self, rhs): + p = float(self) + float(rhs) + return IBMFloat.from_float(p) if isinstance(rhs, IBMFloat) else p + + def __int__(self): + return trunc(self) + + +IBM_FLOAT_ZERO = IBMFloat.from_bytes(IBM_ZERO_BYTES) + + + diff --git a/segpy/portability.py b/segpy/portability.py new file mode 100644 index 0000000..50f506b --- /dev/null +++ b/segpy/portability.py @@ -0,0 +1,78 @@ +import os +import sys + +EMPTY_BYTE_STRING = b'' if sys.version_info >= (3, 0) else '' + + +def seekable(fh): + """Determine whether a file-like object supports seeking. + + Args: + fh: The file-like-object to be tested. + + Returns: + True if the file supports seeking, otherwise False. + """ + try: + return fh.seekable() + except AttributeError: + try: + pos = fh.tell() + try: + fh.seek(0, os.SEEK_END) + finally: + fh.seek(pos) + except AttributeError: + return False + return True + + +if sys.version_info >= (3, 0): + long_int = int +else: + long_int = long + + +if sys.version_info >= (3, 0): + def byte_string(integers): + return bytes(integers) +else: + def byte_string(integers): + return EMPTY_BYTE_STRING.join(chr(i) for i in integers) + + +if sys.version_info >= (3, 0): + import reprlib + reprlib = reprlib # Keep the static analyzer happy +else: + import repr as reprlib + +if sys.version_info >= (3, 0): + izip = zip + from itertools import zip_longest as izip_longest +else: + from itertools import (izip, izip_longest) + izip = izip # Keep the static analyzer happy + izip_longest = izip_longest # Keep the static analyzer happy + + +if sys.version_info >= (3, 0): + def four_bytes(byte_str): + a, b, c, d = byte_str[:4] + return a, b, c, d +else: + def four_bytes(byte_str): + a = ord(byte_str[0]) + b = ord(byte_str[1]) + c = ord(byte_str[2]) + d = ord(byte_str[3]) + return a, b, c, d + +if sys.version_info >= (3, 0): + unicode = str +else: + unicode = unicode + + + + diff --git a/segpy/reader.py b/segpy/reader.py new file mode 100644 index 0000000..c371d9b --- /dev/null +++ b/segpy/reader.py @@ -0,0 +1,661 @@ +from __future__ import print_function +from segpy.encoding import ASCII + +from segpy.portability import seekable +from segpy.util import file_length, filename_from_handle +from segpy.datatypes import DATA_SAMPLE_FORMAT, CTYPE_DESCRIPTION, CTYPES, size_in_bytes +from segpy.toolkit import (extract_revision, + bytes_per_sample, + read_binary_reel_header, + read_trace_header, + catalog_traces, + read_binary_values, + compile_trace_header_format, + REEL_HEADER_NUM_BYTES, + TRACE_HEADER_NUM_BYTES, + read_textual_reel_header, + read_extended_textual_headers, + guess_textual_header_encoding) + + +def create_reader(fh, encoding=None, endian='>', progress=None): + """Create a SegYReader (or one of its subclasses) based on performing + a scan of SEG Y data. + + This function is the preferred method for creating SegYReader + objects. It reads basic header information and attempts to build + indexes for traces, CDP numbers (for 2D surveys), and inline and + cross line co-ordinates (for 3D surveys) to facilitate subsequent + random-access to traces. + + Args: + fh: A file-like-object open in binary mode positioned such + that the beginning of the reel header will be the next + byte to be read. For disk-based SEG Y files, this is the + beginning of the file. + + encoding: An optional text encoding for the textual headers. If + None (the default) a heuristic will be used to guess the + header encoding. + + endian: '>' for big-endian data (the standard and default), '<' + for little-endian (non-standard) + + progress: A unary callable which will be passed a number + between zero and one indicating the progress made. If + provided, this callback will be invoked at least once with + an argument equal to one. + + Raises: + ValueError: ``fh`` is unsuitable for some reason, such as not + being open, not being seekable, not being in + binary mode, or being too short. + + Returns: + A SegYReader object. Depending on the exact type of the + SegYReader returned different capabilities may be + available. Inspect the returned object to determine these + capabilities, or be prepared for capabilities not defined in + the SegYReader base class to be unavailable. The underlying + file-like object must remain open for the duration of use of + the returned reader object. It is the caller's responsibility + to close the underlying file. + + Example: + + with open('my_seismic_data.sgy', 'rb') as fh: + reader = create_reader(fh) + print(reader.num_traces()) + + """ + if hasattr(fh, 'encoding') and fh.encoding is not None: + raise TypeError( + "SegYReader must be provided with a binary mode file object") + + if not seekable(fh): + raise TypeError( + "SegYReader must be provided with a seekable file object") + + if fh.closed: + raise ValueError( + "SegYReader must be provided with an open file object") + + num_file_bytes = file_length(fh) + if num_file_bytes < REEL_HEADER_NUM_BYTES: + raise ValueError( + "SEG Y file {!r} of {} bytes is too short".format( + filename_from_handle(fh), + num_file_bytes)) + + if endian not in ('<', '>'): + raise ValueError("Unrecognised endian value {!r}".format(endian)) + + if encoding is None: + encoding = guess_textual_header_encoding(fh) + + if encoding is None: + encoding = ASCII + + textual_reel_header = read_textual_reel_header(fh, encoding) + binary_reel_header = read_binary_reel_header(fh, endian) + extended_textual_header = read_extended_textual_headers(fh, binary_reel_header, encoding) + revision = extract_revision(binary_reel_header) + bps = bytes_per_sample(binary_reel_header, revision) + + trace_offset_catalog, trace_length_catalog, cdp_catalog, line_catalog = catalog_traces(fh, bps, endian, progress) + + if cdp_catalog is not None and line_catalog is None: + return SegYReader2D(fh, textual_reel_header, binary_reel_header, extended_textual_header, trace_offset_catalog, + trace_length_catalog, cdp_catalog, encoding, endian) + + if cdp_catalog is None and line_catalog is not None: + return SegYReader3D(fh, textual_reel_header, binary_reel_header, extended_textual_header, trace_offset_catalog, + trace_length_catalog, line_catalog, encoding, endian) + + return SegYReader(fh, textual_reel_header, binary_reel_header, extended_textual_header, trace_offset_catalog, + trace_length_catalog, encoding, endian) + + +class SegYReader(object): + """A basic SEG Y reader. + + Use to obtain read the reel header, the trace_samples headers or trace_samples + values. Traces can be accessed only by trace_samples index. + """ + + def __init__(self, + fh, + textual_reel_header, + binary_reel_header, + extended_textual_headers, + trace_offset_catalog, + trace_length_catalog, + encoding, + endian='>'): + """Initialize a SegYReader around a file-like-object. + + Note: + Usually a SegYReader is most easily constructed using the + create_reader() function. + + Args: + fh: A file-like object, which must support seeking and + support binary reading. + + textual_reel_header: A sequence of forty 80-character Unicode strings + containing header data. + + binary_reel_header: A dictionary containing reel header data. + + extended_textual_headers: A sequence of sequences of Unicode strings. + + trace_offset_catalog: A mapping from zero-based trace_samples index to + the byte-offset to individual traces within the file. + + trace_length_catalog: A mapping from zero-based trace_samples index to the + number of samples in that trace_samples. + + encoding: Either ASCII or EBCDIC. + + endian: '>' for big-endian data (the standard and default), '<' for + little-endian (non-standard) + + """ + self._fh = fh + self._endian = endian + self._encoding = encoding + self._trace_header_format = compile_trace_header_format(self._endian) + + self._textual_reel_header = textual_reel_header + self._binary_reel_header = binary_reel_header + self._extended_textual_headers = extended_textual_headers + + self._trace_offset_catalog = trace_offset_catalog + self._trace_length_catalog = trace_length_catalog + + self._revision = extract_revision(self._binary_reel_header) + self._bytes_per_sample = bytes_per_sample( + self._binary_reel_header, self.revision) + + def trace_indexes(self): + """An iterator over zero-based trace_samples indexes. + + Returns: + An iterator which yields integers in the range zero to + num_traces() - 1 + """ + return iter(self._trace_offset_catalog) + + def num_traces(self): + """The number of traces""" + return len(self._trace_offset_catalog) + + def max_num_trace_samples(self): + """The number of samples in the trace_samples with the most samples.""" + return self._trace_length_catalog.value_max() + + def num_trace_samples(self, trace_index): + """The number of samples in the specified trace_samples.""" + return self._trace_length_catalog[trace_index] + + def trace_samples(self, trace_index, start=None, stop=None): + """Read a specific trace_samples. + + Args: + trace_index: An integer in the range zero to num_traces() - 1 + + start: Optional zero-based start sample index. The default + is to read from the first (i.e. zeroth) sample. + + stop: Optional zero-based stop sample index. Following Python + slice convention this is one beyond the end. + + Returns: + A sequence of numeric trace_samples samples. + + Example: + + first_trace_samples = segy_reader.trace_samples(0) + part_of_second_trace_samples = segy_reader.trace_samples(1, 1000, 2000) + """ + if not (0 <= trace_index < self.num_traces()): + raise ValueError("Trace index out of range.") + + num_samples_in_trace = self.num_trace_samples(trace_index) + + start_sample = start if start is not None else 0 + stop_sample = stop if stop is not None else num_samples_in_trace + + if not (0 <= stop_sample <= num_samples_in_trace): + raise ValueError("trace_samples(): stop value {} out of range 0 to {}" + .format(stop, num_samples_in_trace)) + + if not (0 <= start_sample <= stop_sample): + raise ValueError("trace_samples(): start value {} out of range 0 to {}" + .format(start, stop_sample)) + + dsf = self._binary_reel_header['DataSampleFormat'] + ctype = DATA_SAMPLE_FORMAT[dsf] + start_pos = (self._trace_offset_catalog[trace_index] + + TRACE_HEADER_NUM_BYTES + + start_sample * size_in_bytes(CTYPES[ctype])) + num_samples_to_read = stop_sample - start_sample + + trace_values = read_binary_values( + self._fh, start_pos, ctype, num_samples_to_read, self._endian) + return trace_values + + def trace_header(self, trace_index): + """Read a specific trace_samples. + + Args: + trace_index: An integer in the range zero to num_traces() - 1 + + Returns: + A TraceHeader corresponding to the requested trace_samples. + + Example: + + first_trace_header, first_trace_samples = segy_reader.trace_samples(0) + """ + if not (0 <= trace_index < self.num_traces()): + raise ValueError("Trace index {} out of range".format(trace_index)) + pos = self._trace_offset_catalog[trace_index] + trace_header = read_trace_header(self._fh, self._trace_header_format, pos) + return trace_header + + @property + def dimensionality(self): + """The spatial dimensionality of the data. + + Returns: + 3 for 3D seismic volumes, 2 for 2D seismic lines, 1 for a + single trace_samples, otherwise 0. + + """ + return self._dimensionality() + + def _dimensionality(self): + return 1 if self.num_traces() == 1 else 0 + + @property + def textual_reel_header(self): + """The textual real header. + + An immutable sequence of forty Unicode strings each 80 characters long. + """ + return self._textual_reel_header + + @property + def binary_reel_header(self): + """The binary reel header. + + A dictionary containing data from the reel header. + """ + return self._binary_reel_header + + @property + def extended_textual_header(self): + """A sequence of sequences of Unicode strings. + + If there were no headers, the sequence will be empty. + """ + return self._extended_textual_headers + + + @property + def filename(self): + """The filename. + + Returns: + The filename if it could be determined, otherwise '' + """ + return filename_from_handle(self._fh) + + @property + def revision(self): + """The SEG Y revision. + + Returns: + Either datatypes.SEGY_REVISION_0 or datatypes.SEGY_REVISION_1 + """ + return self._revision + + @property + def bytes_per_sample(self): + """The number of bytes per trace_samples sample. + """ + return self._bytes_per_sample + + @property + def data_sample_format(self): + """The data type of the samples in machine-readable form. + + Returns: + One of the values from datatypes.DATA_SAMPLE_FORMAT + """ + return DATA_SAMPLE_FORMAT[self._binary_reel_header['DataSampleFormat']] + + @property + def data_sample_format_description(self): + """A descriptive human-readable description of the data sample format + """ + return CTYPE_DESCRIPTION[self.data_sample_format] + + @property + def encoding(self): + """The encoding, of the data in the underlying file. Either ASCII ('ascii'), + EBCDIC ('cp037') or None.""" + return self._encoding + + @property + def endian(self): + """The endianness of the data in the underlying file. Either '>' for big-endian or '<' for + little endian or None.""" + return self._endian + + +class SegYReader3D(SegYReader): + """A reader for 3D seismic data. + + In addition to the capabilities provided by the SegYReader base + class, this reader provides an index to facilitate random access + to individual traces via crossline and inline co-ordinates. + """ + + def __init__(self, + fh, + textual_reel_header, + binary_reel_header, + extended_textual_headers, + trace_offset_catalog, + trace_length_catalog, + line_catalog, + encoding, + endian='>'): + """Initialize a SegYReader3D around a file-like-object. + + Note: + Usually a SegYReader is most easily constructed using the + create_reader() function. + + Args: + fh: A file-like object, which must support seeking and + support binary reading. + + binary_reel_header: A dictionary containing reel header data. + + trace_offset_catalog: A mapping from zero-based trace_samples indexes to + the byte-offset to individual traces within the file. + + trace_length_catalog: A mapping from zero-based trace_samples indexes to + the number of samples in that trace_samples. + + line_catalog: A mapping from (xline, inline) tuples to + trace_indexes. + + encoding: Either ASCII or EBCDIC. + + endian: '>' for big-endian data (the standard and default), '<' for + little-endian (non-standard) + """ + super(SegYReader3D, self).__init__(fh, textual_reel_header, binary_reel_header, extended_textual_headers, + trace_offset_catalog, trace_length_catalog, encoding, endian) + self._line_catalog = line_catalog + self._num_inlines = None + self._num_xlines = None + + def _dimensionality(self): + return 3 + + def inline_range(self): + """A range encompassing inline numbers. + + The number of inlines within this range can be found with len(reader.inline_range()). + + Returns: + A range() object with start set to the first inline number and stop set to + one beyond the last inline number. The range always has a step of one, although + this should not be taken as meaning that any intermediate inline number generated + by the range is valid. + """ + start = self._line_catalog.key_min()[0] + stop = self._line_catalog.key_max()[0] + 1 + return range(start, stop) + + def num_inlines(self): + """The number of distinct inlines in the survey. + + This number is not necessarily the same as the value returned by + len(reader.inline_range()) as there may be missing inlines within the range. + """ + if self._num_inlines is None: + try: + self._num_inlines = self._line_catalog.i_max - self._line_catalog.i_min + 1 + except AttributeError: + self._num_inlines = len(set(i for i, j in self._line_catalog)) + return self._num_inlines + + def xline_range(self): + """A range encompassing crossline numbers. + + The number of crosslines within this range can be found with len(reader.crossline_range()). + + Returns: + A range() object with start set to the first crossline number and stop set to + one beyond the last crossline number. The range always has a step of one, although + this should not be taken as meaning that any intermediate crossline number generated + by the range is valid. + """ + start = self._line_catalog.key_min()[1] + stop = self._line_catalog.key_max()[1] + 1 + return range(start, stop) + + def num_xlines(self): + """The number of distinct crosslines in the survey. + + This number is not necessarily the same as the value returned by + len(reader.xline_range()) as there may be missing crosslines within the range. + """ + if self._num_xlines is None: + try: + self._num_xlines = self._line_catalog.j_max - self._line_catalog.j_min + 1 + except AttributeError: + self._num_xlines = len(set(j for i, j in self._line_catalog)) + return self._num_xlines + + def inline_xline_numbers(self): + """An iterator over all (inline_number, xline_number) tuples + corresponding to traces. + """ + return iter(self._line_catalog) + + def has_trace_index(self, inline_xline): + """Determine whether a specific trace_samples exists. + + Args: + inline_xline: A 2-tuple of inline number, crossline number. + + Returns: + True if the specified trace_samples exists, otherwise False. + """ + return inline_xline in self._line_catalog + + def trace_index(self, inline_xline): + """Obtain the trace_samples index given an xline and a inline. + + Note: + Do not assume that all combinations of crossline and + inline co-ordinates are valid. The volume may not be + rectangular. Valid values can be obtained from the + inline_xline_numbers() iterator. + + Furthermore, inline and crossline numbers should not be + relied upon to be zero- or one-based indexes (although + they may be). + + Args: + inline_xline: A 2-tuple of inline number, crossline number. + + Returns: + A trace_samples index which can be used with trace_samples(). + """ + return self._line_catalog[inline_xline] + + +class SegYReader2D(SegYReader): + def __init__(self, + fh, + textual_reel_header, + binary_reel_header, + extended_textual_headers, + trace_offset_catalog, + trace_length_catalog, + cdp_catalog, + encoding, + endian='>'): + """Initialize a SegYReader2D around a file-like-object. + + Note: + Usually a SegYReader is most easily constructed using the + create_reader() function. + + Args: + fh: A file-like object, which must support seeking and + support binary reading. + + binary_reel_header: A dictionary containing reel header data. + + trace_catalog_offset: A mapping from zero-based trace_samples index to + the byte-offset to individual traces within the file. + + trace_length_catalog: A mapping from zero-based trace_samples indexes to + the number of samples in that trace_samples. + + cdp_catalog: A mapping from CDP numbers to trace_indexes. + + encoding: Either ASCII or EBCDIC. + + endian: '>' for big-endian data (the standard and default), '<' for + little-endian (non-standard) + """ + super(SegYReader2D, self).__init__(fh, textual_reel_header, binary_reel_header, extended_textual_headers, + trace_offset_catalog, trace_length_catalog, encoding, endian) + self._cdp_catalog = cdp_catalog + + def _dimensionality(self): + return 2 + + def cdp_numbers(self): + """An iterator over all cdp numbers corresponding to traces. + """ + return iter(self._cdp_catalog) + + def cdp_range(self): + """A range encompassing CDP numbers. + + The number of CDPs within this range can be found with len(reader.cdp_range()). + + Returns: + A range() object with start set to the first CDP number and stop set to + one beyond the last CDP number. The range always has a step of one, although + this should not be taken as meaning that any intermediate CDP number generated + by the range is valid. + """ + start = self._cdp_catalog.value_min() + stop = self._cdp_catalog.value_max() + 1 + return range(start, stop) + + def num_cdps(self): + """The number of distinct CDPs. + + This number is not necessarily the same as the value returned by + len(reader.cdp_range()) as there may be missing CDPs. + """ + return len(self._cdp_catalog) + + def has_trace_index(self, cdp_number): + """Determine whether a specified trace_samples exists. + + Args: + cdp_number: A CDP number. + + Returns: + True if the trace_samples exists, otherwise False. + """ + return self._cdp_catalog[cdp_number] + + def trace_index(self, cdp_number): + """Obtain the trace_samples index given an xline and a inline. + + Args: + cdp_number: A CDP number. + + Returns: + A trace_samples index which can be used with trace_samples(). + """ + return self._cdp_catalog[cdp_number] + + +def main(argv=None): + import sys + + if argv is None: + argv = sys.argv[1:] + + class ProgressBar(object): + + def __init__(self, num_chars, character='.'): + self._num_chars = num_chars + self._character = character + self._ratchet = 0 + + def __call__(self, proportion): + existing = self._num_marks(self._ratchet) + required = self._num_marks(proportion) + print(self._character * (required - existing), end='') + self._ratchet = proportion + + def _num_marks(self, p): + return int(round(p * self._num_chars)) + + filename = argv[0] + + with open(filename, 'rb') as segy_file: + segy_reader = create_reader(segy_file, progress=ProgressBar(30)) + print() + print("Filename: ", segy_reader.filename) + print("SEG Y revision: ", segy_reader.revision) + print("Number of traces: ", segy_reader.num_traces()) + print("Data format: ", + segy_reader.data_sample_format_description) + print("Dimensionality: ", segy_reader.dimensionality) + + try: + print("Number of CDPs: ", segy_reader.num_cdps()) + except AttributeError: + pass + + try: + print("Number of inlines: ", segy_reader.num_inlines()) + print("Number of crosslines: ", segy_reader.num_xlines()) + except AttributeError: + pass + + print("=== BEGIN TEXTUAL REEL HEADER ===") + for line in segy_reader.textual_reel_header: + print(line[3:]) + print("=== END TEXTUAL REEL HEADER ===") + print() + print("=== BEGIN EXTENDED TEXTUAL HEADER ===") + print(segy_reader.extended_textual_header) + print("=== END EXTENDED TEXTUAL_HEADER ===") + + for trace_index in segy_reader.trace_indexes(): + trace_header = segy_reader.trace_header(trace_index) + print("Inline {}, Crossline {}, Shotpoint {}".format(trace_header.Inline3D, trace_header.Crossline3D, + trace_header.ShotPoint)) + + +if __name__ == '__main__': + main() diff --git a/revisions.py b/segpy/revisions.py similarity index 88% rename from revisions.py rename to segpy/revisions.py index bf19be9..c6fee03 100644 --- a/revisions.py +++ b/segpy/revisions.py @@ -1,15 +1,18 @@ - -SEGY_REVISION_0 = 0x0000 -SEGY_REVISION_1 = 0x0100 +SEGY_REVISION_0 = 0 +SEGY_REVISION_1 = 1 VARIANTS = {SEGY_REVISION_0: SEGY_REVISION_0, SEGY_REVISION_1: SEGY_REVISION_1, + 0: SEGY_REVISION_0, + 1: SEGY_REVISION_1, 100: SEGY_REVISION_1, 256: SEGY_REVISION_1} + class SegYRevisionError(Exception): pass + def canonicalize_revision(revision): """Canonicalize a SEG Y revision. diff --git a/segpy/textual_reel_header_definition.py b/segpy/textual_reel_header_definition.py new file mode 100644 index 0000000..318b7b2 --- /dev/null +++ b/segpy/textual_reel_header_definition.py @@ -0,0 +1,147 @@ +from segpy.revisions import SEGY_REVISION_0, SEGY_REVISION_1 + +TEMPLATE = """ +C 1 CLIENT { client } COMPANY { company } CREW NO {crew } +C 2 LINE { line } AREA { area } MAP ID { map_id } +C 3 REEL NO {reelnum} DAY-START OF REEL {d} YEAR {yr} OBSERVER {observer } +C 4 INSTRUMENT: MFG { mfg } MODEL { model } SERIAL NO { serial } +C 5 DATA TRACES/RECORD {dtpr} AUXILIARY TRACES/RECORD {atpr } CDP FOLD {cdpfold} +C 6 SAMPLE INTERVAL {intvl} SAMPLES/TRACE {spt} BITS/IN {bi} BYTES/SAMPLE {bps } +C 7 RECORDING FORMAT {rfmt} FORMAT THIS REEL {ftr } MEASUREMENT SYSTEM {measmnt} +C 8 SAMPLE CODE: FLOATING PT {f} FIXED PT {x} FIXED PT-GAIN {g} CORRELATED {cor} +C 9 GAIN TYPE: FIXED {i} BINARY {b} FLOATING POINT {c} OTHER {other } +C10 FILTERS: ALIAS {a }HZ NOTCH {n }HZ BAND {b1}-{b2 }HZ SLOPE {s}-{s2}DB/OCT +C11 SOURCE: TYPE {type } NUMBER/POINT {npt } POINT INTERVAL {point_interval } +C12 PATTERN: {source_pattern } LENGTH {lent} WIDTH {width } +C13 SWEEP: START {ss}HZ END {se}HZ LENGTH {lms}MS CHANNEL NO {q} TYPE {cd } +C14 TAPER: START LENGTH {tsl }MS END LENGTH {tel }MS TYPE {taper_type } +C15 SPREAD: OFFSET {off } MAX DISTANCE {md } GROUP INTERVAL {group_interval } +C16 GEOPHONES: PER GROUP {p} SPACING {y} FREQUENCY {r} MFG {gmfg } MODEL {gmod} +C17 PATTERN: {geophone_pattern } LENGTH {glen} WIDTH {geophone_width } +C18 TRACES SORTED BY: RECORD {u} CDP {v} OTHER { sort_other } +C19 AMPLITUDE RECOVERY: NONE {ar} SPHERICAL DIV {sd } AGC {} OTHER {ar_other } +C20 MAP PROJECTION {map_projection } ZONE ID {zid} COORDINATE UNITS {co_units } +C21 PROCESSING: { processing1 } +C22 PROCESSING: { processing2 } +C23 { unassigned1 } +C24 { unassigned2 } +C25 { unassigned3 } +C26 { unassigned4 } +C27 { unassigned5 } +C28 { unassigned6 } +C29 { unassigned7 } +C30 { unassigned8 } +C31 { unassigned9 } +C32 { unassigned10 } +C33 { unassigned11 } +C34 { unassigned12 } +C35 { unassigned13 } +C36 { unassigned14 } +C37 { unassigned15 } +C38 { unassigned16 } +C39 { unassigned17 } +C40 { end_marker } +""" + + +END_TEXTUAL_HEADER = 'END TEXTUAL HEADER' +END_EBCDIC = 'END EBCDIC' + +END_MARKERS = {SEGY_REVISION_0: END_EBCDIC, + SEGY_REVISION_1: END_TEXTUAL_HEADER} + +TEMPLATE_FIELD_NAMES = {'client': 'client', + 'company': 'company', + 'crew': 'crew_number', + 'line': 'line', + 'area': 'area', + 'map_id': 'map_id', + 'reelnum': 'reel_number', + 'd': 'day_start_of_reel', + 'yr': 'year', + 'observer': 'observer', + 'mfg': 'instrument_manufacturer', + 'model': 'instrument_model', + 'serial': 'instrument_serial', + 'dtpr': 'data_traces_per_record', + 'atpr': 'auxiliary_traces_per_record', + 'cdpfold': 'cdp_fold', + 'intvl': 'sample_interval', + 'spt': 'samples_per_trace', + 'bi': 'bits_per_inch', + 'bps': 'bytes_per_sample', + 'rfmt': 'recording_format', + 'ftr': 'format_this_reel', + 'measmnt': 'measurement_system', + 'f': 'sample_code_floating_point', + 'x': 'sample_code_fixed_point', + 'g': 'sample_code_fixed_point_gain', + 'cor': 'sample_code_correlated', + 'i': 'gain_type_fixed', + 'b': 'gain_type_binary', + 'c': 'gain_type_fixed_point_gain', + 'other': 'gain_type_other', + 'a': 'filters_alias_hz', + 'n': 'filters_notch_hz', + 'b1': 'filters_band_lower_hz', + 'b2': 'filters_band_upper_hz', + 's': 'filters_slope_lower_db_per_oct', + 's2': 'filters_slope_upper_db_per_oct', + 'type': 'source_type', + 'npt': 'source_number_per_point', + 'point_interval': 'source_point_interval', + 'source_pattern': 'source_pattern', + 'lent': 'source_length', + 'width': 'source_width', + 'ss': 'sweep_start_hz', + 'se': 'sweep_end_hz', + 'lms': 'sweep_length_ms', + 'q': 'sweep_channel_number', + 'cd': 'sweep_type', + 'tsl': 'taper_start_length_ms', + 'tel': 'taper_end_length_ms', + 'taper_type': 'taper_type', + 'off': 'spread_offset', + 'md': 'spread_max_distance', + 'group_interval': 'spread_group_interval', + 'p': 'geophones_per_group', + 'y': 'geophone_spacing', + 'r': 'geophone_frequency', + 'gmfg': 'geophone_manufacturer', + 'gmod': 'geophone_model', + 'geophone_pattern': 'geophone_pattern', + 'glen': 'geophone_length', + 'geophone_width': 'geophone_width', + 'u': 'traces_sorted_by_record', + 'v': 'traces_sorted_by_cdp', + 'sort_other': 'traces_sorted_by_other', + 'ar': 'amplitude_recovery_none', + 'sd': 'amplitude_recovery_spherical_div', + '': 'amplitude_recovery_agc', + 'ar_other': 'amplitude_recovery_other', + 'map_projection': 'map_projection', + 'zid': 'zone_id', + 'co_units': 'coordinate_units', + 'processing1': 'processing1', + 'processing2': 'processing2', + 'unassigned1': 'unassigned1', + 'unassigned2': 'unassigned2', + 'unassigned3': 'unassigned3', + 'unassigned4': 'unassigned4', + 'unassigned5': 'unassigned5', + 'unassigned6': 'unassigned6', + 'unassigned7': 'unassigned7', + 'unassigned8': 'unassigned8', + 'unassigned9': 'unassigned9', + 'unassigned10': 'unassigned10', + 'unassigned11': 'unassigned11', + 'unassigned12': 'unassigned12', + 'unassigned13': 'unassigned13', + 'unassigned14': 'unassigned14', + 'unassigned15': 'unassigned15', + 'unassigned16': 'unassigned16', + 'unassigned17': 'unassigned17', + 'end_marker': 'end_marker' + } + +INV_TEMPLATE_FIELD_NAMES = dict((v, k) for k, v in TEMPLATE_FIELD_NAMES.items()) diff --git a/segpy/toolkit.py b/segpy/toolkit.py new file mode 100644 index 0000000..1769c8a --- /dev/null +++ b/segpy/toolkit.py @@ -0,0 +1,899 @@ +from __future__ import print_function + +from array import array +from collections import namedtuple, OrderedDict +import itertools +import os +import struct +import re +import logging + +from segpy import textual_reel_header_definition + + +from segpy.catalog import CatalogBuilder +from segpy.datatypes import CTYPES, size_in_bytes +from segpy.encoding import guess_encoding, is_supported_encoding, UnsupportedEncodingError +from segpy.binary_reel_header_definition import HEADER_DEF +from segpy.ibm_float import IBMFloat +from segpy.revisions import canonicalize_revision +from segpy.trace_header_definition import TRACE_HEADER_DEF +from segpy.util import file_length, batched, pad, complementary_intervals, NATIVE_ENDIANNESS +from segpy.portability import EMPTY_BYTE_STRING, izip_longest + +HEADER_NEWLINE = '\r\n' + +CARD_LENGTH = 80 +CARDS_PER_HEADER = 40 + +TEXTUAL_HEADER_NUM_BYTES = CARD_LENGTH * CARDS_PER_HEADER +BINARY_HEADER_NUM_BYTES = 400 +REEL_HEADER_NUM_BYTES = TEXTUAL_HEADER_NUM_BYTES + BINARY_HEADER_NUM_BYTES +TRACE_HEADER_NUM_BYTES = 240 + +END_TEXT_STANZA = "((SEG: EndText))" + + +def logger(): + # Defer logger creation until the module is *used* rather than imported. + return logging.getLogger(__name__) + + +def extract_revision(binary_reel_header): + """Obtain the SEG Y revision from the reel header. + + Args: + binary_reel_header: A dictionary containing a reel header, such as obtained + from read_binary_reel_header() + + Returns: + One of the constants revisions.SEGY_REVISION_0 or + revisions.SEGY_REVISION_1 + """ + raw_revision = binary_reel_header['SegyFormatRevisionNumber'] + return canonicalize_revision(raw_revision) + + +def num_extended_textual_headers(binary_reel_header): + """Obtain the number of 3200 byte extended textual file headers. + + A value of zero indicates there are no Extended Textual File Header records + (i.e. this file has no Extended Textual File Header(s)). A value of -1 indicates + that there are a variable number of Extended Textual File Header records and the + end of the Extended Textual File Header is denoted by an ((SEG: EndText)) stanza + in the final record. A positive value indicates that there are exactly that many + Extended Textual File Header records. + """ + num_ext_headers = binary_reel_header['NumberOfExtTextualHeaders'] + return num_ext_headers + + +def bytes_per_sample(binary_reel_header, revision): + """Determine the number of bytes per sample from the reel header. + + Args: + binary_reel_header: A dictionary containing a reel header, such as obtained + from read_binary_reel_header() + + revision: One of the constants revisions.SEGY_REVISION_0 or + revisions.SEGY_REVISION_1 + + Returns: + An integer number of bytes per sample. + """ + dsf = binary_reel_header['DataSampleFormat'] + bps = HEADER_DEF["DataSampleFormat"]["bps"][revision][dsf] + return bps + + +def samples_per_trace(binary_reel_header): + """Determine the number of samples per trace_samples from the reel header. + + Note: There is no requirement for all traces to be of the same length, + so this value should be considered indicative only, and as such is + mostly useful in the absence of other information. The actual number + of samples for a specific trace_samples should be retrieved from individual + trace_samples headers. + + Args: + binary_reel_header: A dictionary containing a reel header, such as obtained + from read_binary_reel_header() + + Returns: + An integer number of samples per trace_samples + """ + return binary_reel_header['ns'] + + +def trace_length_bytes(binary_reel_header, bps): + """Determine the trace_samples length in bytes from the reel header. + + Note: There is no requirement for all traces to be of the same length, + so this value should be considered indicative only, and as such is + mostly useful in the absence of other information. The actual number + of samples for a specific trace_samples should be retrieved from individual + trace_samples headers. + + Args: + binary_reel_header: A dictionary containing a reel header, such as obtained + from read_binary_reel_header() + + bps: The number of bytes per sample, such as obtained from a call to + bytes_per_sample() + + """ + return samples_per_trace(binary_reel_header) * bps + TRACE_HEADER_NUM_BYTES + + +def guess_textual_header_encoding(fh): + fh.seek(0) + raw_header = fh.read(TEXTUAL_HEADER_NUM_BYTES) + encoding = guess_encoding(raw_header) + return encoding + + +def read_textual_reel_header(fh, encoding): + """Read the SEG Y card image header, also known as the textual header + + Args: + fh: A file-like object open in binary mode positioned such that the + beginning of the textual header will be the next byte to read. + + encoding: Either 'cp037' for EBCDIC or 'ascii' for ASCII. + + Returns: + A tuple of forty Unicode strings (Python 2: unicode, Python 3: str) + containing the transcoded header data. + """ + fh.seek(0) + raw_header = fh.read(TEXTUAL_HEADER_NUM_BYTES) + + num_bytes_read = len(raw_header) + if num_bytes_read < TEXTUAL_HEADER_NUM_BYTES: + raise EOFError("Only {} bytes of {} byte textual reel header could be read" + .format(num_bytes_read, TEXTUAL_HEADER_NUM_BYTES)) + + lines = tuple(bytes(raw_line).decode(encoding) for raw_line in batched(raw_header, CARD_LENGTH)) + return lines + + +def read_binary_reel_header(fh, endian='>'): + """Read the SEG Y binary reel header. + + Args: + fh: A file-like object open in binary mode. Binary header is assumed to + be at an offset of 3200 bytes from the beginning of the file. + + endian: '>' for big-endian data (the standard and default), '<' for + little-endian (non-standard) + """ + fh.seek(TEXTUAL_HEADER_NUM_BYTES) + reel_header = {} + for key in HEADER_DEF: + pos = HEADER_DEF[key]['pos'] + ctype = HEADER_DEF[key]['type'] + values = tuple(read_binary_values(fh, pos, ctype, 1, endian)) + reel_header[key] = values[0] + return reel_header + + +def has_end_text_stanza(ext_header): + """Determine whether the header is the end text stanza. + + Args: + ext_header: A sequence of forty CARD_LENGTH character Unicode strings. + + Returns: + True if the header is the SEG Y Revision 1 end text header, + otherwise False. + """ + return END_TEXT_STANZA in ext_header[0] + + +def read_extended_headers_until_end(fh, encoding): + """Read an unspecified number of extended textual headers, until the end-text header is found. + + Args: + fh: A file-like object open in binary mode. The first of any extended textual headers + is assumed to be at an offset of 3600 bytes from the beginning of the file + (immediately following the binary reel header). + + encoding: Optional encoding of the header in the file. If None (the + default) a reliable heuristic will be used to guess the encoding. + Typically 'cp037' for EBCDIC or 'ascii' for ASCII. + + Returns: + A list of tuples each containing forty CARD_LENGTH character Unicode strings. If present, the end_text + stanza is excluded. + """ + extended_headers = [] + while True: + ext_header = read_textual_reel_header(fh, encoding) + extended_headers.append(ext_header) + if has_end_text_stanza(ext_header): + break + return extended_headers + + +def read_extended_headers_counted(fh, num_expected, encoding): + """Read a specified number of extended textual headers. + + If an end-text stanza is located prematurely (in anything other than the last expected header) + reading will be terminated and a warning logged. + + Args: + fh: A file-like object open in binary mode. The first of any extended textual headers + is assumed to be at an offset of 3600 bytes from the beginning of the file + (immediately following the binary reel header). + + num_expected: A non-negative integer of headers. + + encoding: Optional encoding of the header in the file. If None (the + default) a reliable heuristic will be used to guess the encoding. + Typically 'cp037' for EBCDIC or 'ascii' for ASCII. + + Returns: + A list of tuples each containing forty CARD_LENGTH -character Unicode strings. + """ + assert num_expected >= 0 + extended_headers = [] + for i in range(num_expected): + ext_header = read_textual_reel_header(fh, encoding) + if has_end_text_stanza(ext_header): + if i != num_expected - 1: + logger().warning("Unexpected end-text extended header.") + break + extended_headers.append(ext_header) + + return extended_headers + + +def read_extended_textual_headers(fh, binary_reel_header, encoding): + """Read any extended textual reel headers. + + Args: + fh: A file-like object open in binary mode. The first of any extended textual headers + is assumed to be at an offset of 3600 bytes from the beginning of the file + (immediately following the binary reel header). + + binary_reel_header: A dictionary containing data read from the binary + reel header by the read_binary_reel_header() function. + + encoding: Optional encoding of the header in the file. If None (the + default) a reliable heuristic will be used to guess the encoding. + Typically 'cp037' for EBCDIC or 'ascii' for ASCII. + + Returns: + A sequence of sequences of Unicode strings representing headers of lines of characters. The length of the + outer sequence will be equal to the number of extended headers read. Each item in the outer sequence will be + a sequence of exactly forty Unicode strings. To combine the headers into a single string, consider using + concatenate_extended_textual_headers(). + + Post-condition: + As a post-condition to this function, the file-pointer of fh will be + positioned immediately after the last extended textual header, which + should be the start of the first trace_samples header. + """ + fh.seek(REEL_HEADER_NUM_BYTES) + declared_num_ext_headers = num_extended_textual_headers(binary_reel_header) + + if declared_num_ext_headers < 0: + return read_extended_headers_until_end(fh, encoding) + + return read_extended_headers_counted(fh, declared_num_ext_headers, encoding) + + +_READ_PROPORTION = 0.75 # The proportion of time spent in catalog_traces + # reading the file. Determined empirically. + + +def catalog_traces(fh, bps, endian='>', progress=None): + """Build catalogs to facilitate random access to trace_samples data. + + Note: + This function can take significant time to run, proportional + to the number of traces in the SEG Y file. + + Four catalogs will be build: + + 1. A catalog mapping trace_samples index (0-based) to the position of that + trace_samples header in the file. + + 2. A catalog mapping trace_samples index (0-based) to the number of + samples in that trace_samples. + + 3. A catalog mapping CDP number to the trace_samples index. + + 4. A catalog mapping an (inline, crossline) number 2-tuple to + trace_samples index. + + Args: + fh: A file-like-object open in binary mode, positioned at the + start of the first trace_samples header. + + bps: The number of bytes per sample, such as obtained by a call + to bytes_per_sample() + + endian: '>' for big-endian data (the standard and default), '<' + for little-endian (non-standard) + + progress: A unary callable which will be passed a number + between zero and one indicating the progress made. If + provided, this callback will be invoked at least once with + an argument equal to 1 + + Returns: + A 4-tuple of the form (trace_samples-offset-catalog, + trace_samples-length-catalog, + cdp-catalog, + line-catalog)` where + each catalog is an instance of ``collections.Mapping`` or None + if no catalog could be built. + """ + progress_callback = progress if progress is not None else lambda p: None + + if not callable(progress_callback): + raise TypeError("catalog_traces(): progress callback must be callable") + + trace_header_format = compile_trace_header_format(endian) + + length = file_length(fh) + + pos_begin = fh.tell() + + trace_offset_catalog_builder = CatalogBuilder() + trace_length_catalog_builder = CatalogBuilder() + line_catalog_builder = CatalogBuilder() + alt_line_catalog_builder = CatalogBuilder() + cdp_catalog_builder = CatalogBuilder() + + for trace_number in itertools.count(): + progress_callback(_READ_PROPORTION * pos_begin / length) + fh.seek(pos_begin) + data = fh.read(TRACE_HEADER_NUM_BYTES) + if len(data) < TRACE_HEADER_NUM_BYTES: + break + trace_header = TraceHeader._make(trace_header_format.unpack(data)) + num_samples = trace_header.ns + trace_length_catalog_builder.add(trace_number, num_samples) + samples_bytes = num_samples * bps + trace_offset_catalog_builder.add(trace_number, pos_begin) + # Should we check the data actually exists? + line_catalog_builder.add((trace_header.Inline3D, + trace_header.Crossline3D), + trace_number) + alt_line_catalog_builder.add((trace_header.TraceSequenceFile, + trace_header.cdp), + trace_number) + cdp_catalog_builder.add(trace_header.cdp, trace_number) + pos_end = pos_begin + TRACE_HEADER_NUM_BYTES + samples_bytes + pos_begin = pos_end + + progress_callback(_READ_PROPORTION) + + trace_offset_catalog = trace_offset_catalog_builder.create() + progress_callback(_READ_PROPORTION + (_READ_PROPORTION / 4)) + + trace_length_catalog = trace_length_catalog_builder.create() + progress_callback(_READ_PROPORTION + (_READ_PROPORTION / 2)) + + cdp_catalog = cdp_catalog_builder.create() + progress_callback(_READ_PROPORTION + (_READ_PROPORTION * 3 / 4)) + + line_catalog = line_catalog_builder.create() + + if line_catalog is None: + # Some 3D files put Inline and Crossline numbers in (TraceSequenceFile, cdp) pair + line_catalog = alt_line_catalog_builder.create() + + progress_callback(1) + + return (trace_offset_catalog, + trace_length_catalog, + cdp_catalog, + line_catalog) + + +def read_trace_header(fh, trace_header_format, pos=None): + """Read a trace_samples header. + + Args: + fh: A file-like-object open in binary mode. + + trace_header_format: A Struct object, such as obtained from a + call to compile_trace_header_format() + + pos: The file offset in bytes from the beginning from which the data + is to be read. + + Returns: + A TraceHeader object. + """ + if pos is not None: + fh.seek(pos) + data = fh.read(TRACE_HEADER_NUM_BYTES) + trace_header = TraceHeader._make( + trace_header_format.unpack(data)) + return trace_header + + +def read_binary_values(fh, pos=None, ctype='int32', count=1, endian='>'): + """Read a series of values from a binary file. + + Args: + fh: A file-like-object open in binary mode. + +c + + ctype: The SEG Y data type. + + number: The number of items to be read. + Returns: + A sequence containing count items. + """ + fmt = CTYPES[ctype] + item_size = size_in_bytes(fmt) + block_size = item_size * count + + fh.seek(pos, os.SEEK_SET) + buf = fh.read(block_size) + + if len(buf) < block_size: + raise EOFError("{} bytes requested but only {} available".format( + block_size, len(buf))) + + values = (unpack_ibm_floats(buf, count) + if fmt == 'ibm' + else unpack_values(buf, count, fmt, endian)) + assert len(values) == count + return values + + +def unpack_ibm_floats(data, count): + """Unpack a series of binary-encoded big-endian single-precision IBM floats. + + Args: + data: A sequence of bytes. (Python 2 - a str object, + Python 3 - a bytes object) + + count: The number of floats to be read. + + Returns: + A sequence of floats. + """ + return [IBMFloat.from_bytes(data[i: i+4]) for i in range(0, count * 4, 4)] + + +def unpack_values(buf, count, fmt, endian='>'): + """Unpack a series items from a byte string. + + Args: + data: A sequence of bytes. (Python 2 - a str object, + Python 3 - a bytes object) + + count: The number of floats to be read. + + fmt: A format code (one of the values in the datatype.CTYPES + dictionary) + + endian: '>' for big-endian data (the standard and default), '<' + for little-endian (non-standard) + + Returns: + A sequence of objects with type corresponding to the format code. + """ + a = array(fmt, buf) + if endian != NATIVE_ENDIANNESS: + a.byteswap() + return a + + +def format_standard_textual_header(revision, **kwargs): + """Produce a standard SEG Y textual header. + + Args: + revision: The SEG Y revision. + + **kwargs: Named arguments corresponding to the values in the + textual_reel_header_definition.TEMPLATE_FIELD_NAMES dictionary, + which in turn correspond to the placeholders in the + textual_reel_header_definition.TEMPLATE string. Any omitted + arguments will result in placeholders being replaced by spaces. + If the end_marker argument is not supplied, an appropriate end + marker will be selected based on the SEG Y revision. For standard + end markers consider using textual_reel_header_definition.END_TEXTUAL_HEADER + or textual_reel_header_definition.END_EBCDIC. + + Returns: + A list of forty Unicode strings. + + Usage: + header = format_standard_textual_header(1, + client="Lundin", + company="Western Geco", + crew_number=123, + processing1="Sixty North AS", + sweep_start_hz=10, + sweep_end_hz=1000, + sweep_length_ms=10000, + sweep_channel_number=3, + sweep_type='spread') + + """ + + kwargs.setdefault('end_marker', textual_reel_header_definition.END_MARKERS[revision]) + + template = textual_reel_header_definition.TEMPLATE + + placeholder_slices = parse_template(template) + background_slices = complementary_intervals(placeholder_slices.values(), 0, len(template)) + + chunks = [] + for bg_slice, placeholder in izip_longest(background_slices, placeholder_slices.items()): + + if bg_slice is not None: + chunks.append(template[bg_slice]) + + if placeholder is not None: + ph_name, ph_slice = placeholder + ph_arg_name = textual_reel_header_definition.TEMPLATE_FIELD_NAMES[ph_name] + ph_value = kwargs.pop(ph_arg_name, '') + ph_len = ph_slice.stop - ph_slice.start + substitute = str(ph_value)[:ph_len].ljust(ph_len, ' ') + chunks.append(substitute) + + if len(kwargs) > 0: + raise TypeError("The following keyword arguments did not correspond to template placeholders: {!r}" + .format(list(kwargs.keys()))) + + concatenation = ''.join(chunks) + lines = concatenation.splitlines(keepends=False) + + return lines[1:] # Omit the first and last lines, which are artifacts of the multi-line string template + + +_TEMPLATE_PATTERN = r'\{\s*(\w*)\s*\}' +_TEMPLATE_REGEX = re.compile(_TEMPLATE_PATTERN) + + +def parse_template(template): + """Parse a template to produce a dictionary of placeholders. + + Args: + template: The template string containing { field-name } style fixed-width fields. + + Returns: + A OrderedDict mapping field names to slices objects which can be used to index + into the template string. The order of the entries is the same as the order within + which they occur in the template. + """ + matches = _TEMPLATE_REGEX.finditer(template) + + fields = OrderedDict() + for match in matches: + name = match.group(1) + start = match.start() + end = match.end() + fields[name] = slice(start, end) + + return fields + + +def write_textual_reel_header(fh, lines, encoding): + """Write the SEG Y card image header, also known as the textual header + + Args: + fh: A file-like object open in binary mode positioned such that the + beginning of the textual header will be the next byte to read. + + lines: An iterable series of forty lines, each of which must be a + Unicode string of CARD_LENGTH characters. The first three characters + of each line are often "C 1" to "C40" (as required by the SEG Y + standard) although this is not enforced by this function, since + many widespread SEG Y readers and writers do not adhere to this + constraint. To produce a SEG Y compliant series of header lines + consider using the format_standard_textual_header() function. + + Any lines longer than CARD_LENGTH characters will be truncated without + warning. Any excess lines over CARDS_PER_HEADER will be discarded. Short + or omitted lines will be padded with spaces. + + encoding: Typically 'cp037' for EBCDIC or 'ascii' for ASCII. + + Post-condition: + The file pointer in fh will be positioned at the first byte following the textual + header. + + Raises: + UnsupportedEncodingError: If encoding is neither EBCDIC nor ASCII. + UnicodeError: If the data provided in lines cannot be encoded with the encoding. + """ + if not is_supported_encoding(encoding): + raise UnsupportedEncodingError("Writing textual reel header", encoding) + + fh.seek(0) + + padded_lines = [line.encode(encoding).ljust(CARD_LENGTH, ' '.encode(encoding))[:CARD_LENGTH] + for line in pad(lines, padding='', size=CARDS_PER_HEADER)] + joined_header = EMPTY_BYTE_STRING.join(padded_lines) + assert len(joined_header) == 3200 + fh.write(joined_header) + + fh.seek(TEXTUAL_HEADER_NUM_BYTES) + + +def write_binary_reel_header(fh, binary_reel_header, endian='>'): + """Write the binary_reel_header to the given file-like object. + + Args: + fh: A file-like object open in binary mode for writing. + + binary_reel_header: A dictionary of values using a subset of the keys + in binary_reel_header_definition.HEADER_DEF associated with + compatible values. + + Post-condition: + The file pointer for fh will be positioned at the first byte following + the binary reel header. + """ + + for key in HEADER_DEF: + pos = HEADER_DEF[key]['pos'] + ctype = HEADER_DEF[key]['type'] + value = binary_reel_header[key] if key in binary_reel_header else HEADER_DEF[key]['def'] + write_binary_values(fh, [value], ctype, pos, endian) + + fh.seek(REEL_HEADER_NUM_BYTES) + + +def format_extended_textual_header(text, encoding, include_text_stop=False): + """Format a string into pages and line suitable for an extended textual header. + + Args + text: An arbitrary text string. Any universal newlines will be preserved. + + encoding: Either ASCII ('ascii') or EBCDIC ('cp037') + + include_text_stop: If True, a text stop stanza header will be appended, otherwise not. + """ + + if not is_supported_encoding(encoding): + raise UnsupportedEncodingError("Extended textual header", encoding) + + # According to the standard: "The Extended Textual File Header consists of one or more 3200-byte records, each + # record containing 40 lines of textual card-image text." It goes on "... Each line in an Extended Textual File + # Header ends in carriage return and linefeed (EBCDIC 0D25 or ASCII 0D0A)." Given that we're dealing with fixed- + # length (80 byte) lines, this implies that we have 78 bytes of space into which we can encode the content of each + # line, which must be left-justified and padded with spaces. + + width = CARD_LENGTH - len(HEADER_NEWLINE) + original_lines = text.splitlines() + + # Split overly long lines (i.e. > 78) and pad too-short lines with spaces + lines = [] + for original_line in original_lines: + padded_lines = (pad_and_terminate_header_line(original_line[i:i+width], width) + for i in range(0, len(original_line), width)) + lines.extend(padded_lines) + + pages = list(batched(lines, 40, pad_and_terminate_header_line('', width))) + + if include_text_stop: + stop_page = format_extended_textual_header(END_TEXT_STANZA, encoding)[0] + pages.append(stop_page) + + return pages + + +def pad_and_terminate_header_line(line, width): + return line.ljust(width, ' ') + HEADER_NEWLINE + + +def write_extended_textual_headers(fh, pages, encoding): + """Write extended textual headers. + + Args: + fh: A file-like object open in binary mode for writing. + + pages: An iterables series of sequences of Unicode strings, where the outer iterable + represents 3200 byte pages, each comprised of a sequence of exactly 40 strings of nominally 80 characters + each. Although Unicode strings are accepted, and when encoded they should result in exact 80 bytes + sequences. To produce a valid data structure for pages, consider using format_extended_textual_header() + + encoding: Either 'cp037' for EBCDIC or 'ascii' for ASCII. + + Post-condition: + The file pointer in fh will be position at the first byte after the extended textual headers, which is + also the first byte of the first trace-header. + + Raises: + ValueError: If the provided header data has the wrong shape. + UnicodeError: If the textual data could not be encoded into the specified encoding. + + """ + + if not is_supported_encoding(encoding): + raise UnsupportedEncodingError("Writing extended textual header", encoding) + + fh.seek(REEL_HEADER_NUM_BYTES) + + encoded_pages = [] + for page_index, page in enumerate(pages): + encoded_page = [] + # TODO: Share some of this code with writing the textual reel header. + for line_index, line in enumerate(page): + encoded_line = line.encode(encoding) + num_encoded_bytes = len(encoded_line) + if num_encoded_bytes != CARD_LENGTH: + raise ValueError("Extended textual header line {} of page {} at {} bytes is not " + "{} bytes".format(line_index, page_index, num_encoded_bytes, CARD_LENGTH)) + encoded_page.append(encoded_line) + num_encoded_lines = len(encoded_page) + if num_encoded_lines != CARDS_PER_HEADER: + raise ValueError("Extended textual header page {} number of " + "lines {} is not {}".format(num_encoded_lines, CARDS_PER_HEADER)) + encoded_pages.append(encoded_page) + + for encoded_page in encoded_pages: + concatenated_page = EMPTY_BYTE_STRING.join(encoded_page) + assert(len(concatenated_page) == TEXTUAL_HEADER_NUM_BYTES) + fh.write(concatenated_page) + + +def write_trace_header(fh, trace_header, trace_header_format, pos=None): + """Write a TraceHeader to file. + + Args: + fh: A file-like object open in binary mode for writing. + + trace_header: A TraceHeader object. + + trace_header_format: A Struct object, such as obtained from a + call to compile_trace_header_format() + + pos: An optional file offset in bytes from the beginning of the + file. Defaults to the current file position. + """ + if pos is not None: + fh.seek(pos, os.SEEK_SET) + buf = trace_header_format.pack(*trace_header) + fh.write(buf) + + +def write_trace_samples(fh, samples, ctype='l', pos=None, endian='>'): + """Write a trace samples to a file + + Args: + fh: A file-like-object open for writing in binary mode. + + values: An iterable series of values. + + ctype: The SEG Y data type. + + pos: An optional offset from the beginning of the file. If omitted, + any writing is done at the current file position. + + endian: '>' for big-endian data (the standard and default), '<' + for little-endian (non-standard) + """ + write_binary_values(fh, samples, ctype, pos, endian) + + +def write_binary_values(fh, values, ctype, pos=None, endian='>'): + """Write a series of values to a file. + + Args: + fh: A file-like-object open for writing in binary mode. + + values: An iterable series of values. + + ctype: The SEG Y data type. + + pos: An optional offset from the beginning of the file. If omitted, + any writing is done at the current file position. + + endian: '>' for big-endian data (the standard and default), '<' + for little-endian (non-standard) + """ + fmt = CTYPES[ctype] + + if pos is not None: + fh.seek(pos, os.SEEK_SET) + + buf = (pack_ibm_floats(values) + if fmt == 'ibm' + else pack_values(values, fmt, endian)) + + fh.write(buf) + + +def pack_ibm_floats(values): + """Pack floats into binary-encoded big-endian single-precision IBM floats. + + Args: + values: An iterable series of numeric values. + + Returns: + A sequence of bytes. (Python 2 - a str object, Python 3 - a bytes + object) + """ + return EMPTY_BYTE_STRING.join(bytes(IBMFloat.from_real(value)) for value in values) + + +def pack_values(values, fmt, endian='>'): + """Pack values into binary encoded big-endian byte strings. + + Args: + values: An iterable series of values. + + fmt: A format code (one of the values in the datatype.CTYPES + dictionary) + + endian: '>' for big-endian data (the standard and default), '<' + for little-endian (non-standard) + """ + c_format = '{}{}{}'.format(endian, len(values), fmt) + return struct.pack(c_format, *values) + + +# TODO: Consider generalising the below to also produce a ReelHeader record. Then modify +# read_binary_reel_header() to return such a record, and write_binary_reel_header() to accept such +# a record. + + +_TraceAttributeSpec = namedtuple('Record', ['name', 'pos', 'type']) + + +def compile_trace_header_format(endian='>'): + """Compile a format string for use with the struct module from the + trace_samples header definition. + + Args: + endian: '>' for big-endian data (the standard and default), '<' for + little-endian (non-standard) + + Returns: + A string which can be used with the struct module for parsing + trace_samples headers. + + """ + + record_specs = sorted( + [_TraceAttributeSpec(name, + TRACE_HEADER_DEF[name]['pos'], + TRACE_HEADER_DEF[name]['type']) + for name in TRACE_HEADER_DEF], + key=lambda r: r.pos) + + fmt = [endian] + length = 0 + for record_spec in record_specs: + + shortfall = length - record_spec.pos + if shortfall: + fmt.append(str(shortfall) + 'x') # Ignore bytes + length += shortfall + + ctype = CTYPES[record_spec.type] + fmt.append(ctype) + length += size_in_bytes(ctype) + + assert length == TRACE_HEADER_NUM_BYTES + + return struct.Struct(''.join(fmt)) + + +def _compile_trace_header_record(): + """Build a TraceHeader namedtuple from the trace_samples header definition""" + record_specs = sorted( + [_TraceAttributeSpec(name, + TRACE_HEADER_DEF[name]['pos'], + TRACE_HEADER_DEF[name]['type']) + for name in TRACE_HEADER_DEF], + key=lambda r: r.pos) + return namedtuple('TraceHeader', + (record_spec.name for record_spec in record_specs)) + + +TraceHeader = _compile_trace_header_record() + diff --git a/trace_header_definition.py b/segpy/trace_header_definition.py similarity index 99% rename from trace_header_definition.py rename to segpy/trace_header_definition.py index edaa6f3..149db4c 100644 --- a/trace_header_definition.py +++ b/segpy/trace_header_definition.py @@ -1,4 +1,4 @@ -from revisions import SEGY_REVISION_0, SEGY_REVISION_1 +from segpy.revisions import SEGY_REVISION_0, SEGY_REVISION_1 TRACE_HEADER_DEF = {"TraceSequenceLine": {"pos": 0, "type": "int32"}} TRACE_HEADER_DEF["TraceSequenceFile"] = {"pos": 4, "type": "int32"} diff --git a/segpy/util.py b/segpy/util.py new file mode 100644 index 0000000..7b4508e --- /dev/null +++ b/segpy/util.py @@ -0,0 +1,240 @@ +import itertools +import time +import os +import sys + +from segpy.portability import izip + +NATIVE_ENDIANNESS = '<' if sys.byteorder == 'little' else '>' + +UNSET = object() + +def pairwise(iterable): + """Pairwise iteration. + + Args: + iterable: An iterable series. + + Returns: + An iterator over 2-tuples. + """ + a, b = itertools.tee(iterable) + next(b, None) + return izip(a, b) + + +def batched(iterable, batch_size, padding=UNSET): + """Batch an iterable series into equal sized batches. + + Args: + iterable: The series to be batched. + + batch_size: The size of the batch. Must be at least one. + + padding: Optional value used to pad the final batch to batch_size. If + omitted, the final batch may be smaller than batch_size. + + Yields: + A series of lists, each containing batch_size items from iterable. + + Raises: + ValueError: If batch_size is less than one. + """ + if batch_size < 1: + raise ValueError("Batch size {} is not at least one.".format(batch_size)) + + pending = [] + + for item in iterable: + pending.append(item) + if len(pending) == batch_size: + batch = pending + pending = [] + yield batch + + num_left_over = len(pending) + if num_left_over > 0: + if padding is not UNSET: + pending.extend([padding] * (batch_size - num_left_over)) + yield pending + + +def pad(iterable, padding=None, size=None): + if size is None: + return itertools.chain(iterable, itertools.repeat(padding)) + return itertools.islice(pad(iterable, padding), size) + + +def complementary_intervals(intervals, start=None, stop=None): + """Compute a complementary set of intervals which alternate with given intervals to form a contiguous range. + + Given, + + Start Stop + [-----) [-----) [----) + + produces, + + [--) [----) [-) [---) + + Args: + intervals: An sequence of at least one existing slices or ranges. The type of the first interval (slice or + range) is used as the result type. + start: An optional start index, defaults to the start of the first slice. + stop: An optional one-beyond-the-end index, defaults to the stop attribute of the last slice. + + Yields: + A complementary series of slices which alternate with the supplied slices. The number of returned + slices will always be len(slices) + 1 since both leading and trailing slices will always be returned. + Note the some of the returned slices may be 'empty' (having zero length). + """ + if len(intervals) < 1: + raise ValueError("intervals must contain at least one interval (slice or range) object") + + interval_type = type(intervals[0]) + + if start is None: + start = intervals[0].start + + if stop is None: + stop = intervals[-1].stop + + index = start + for s in intervals: + yield interval_type(index, s.start) + index = s.stop + + yield interval_type(index, stop) + + +def roundrobin(*iterables): + """Take items from each iterable in turn until all iterables are exhausted. + + roundrobin('ABC', 'D', 'EF') --> A D E B F C + """ + # Recipe credited to George Sakkis + pending = len(iterables) + nexts = itertools.cycle(iter(it).__next__ for it in iterables) + while pending: + try: + for n in nexts: + yield n() + except StopIteration: + pending -= 1 + nexts = itertools.cycle(itertools.islice(nexts, pending)) + + +def contains_duplicates(sorted_iterable): + """Determine in an iterable series contains duplicates. + + Args: + sorted_iterable: Any iterable series which must be sorted in either + ascending or descending order. + + Returns: + True if sorted_iterable contains duplicates, otherwise False. + """ + for a, b in pairwise(sorted_iterable): + if a == b: + return True + return False + + +def measure_stride(iterable): + """Determine whether successive numeric items differ by a constant amount. + + Args: + iterable: An iterable series of numeric values. + + Returns: + The difference between successive values (e.g. item[1] - item[0]) if + that difference is the same between all successive pairs, otherwise + None. + """ + stride = None + for a, b in pairwise(iterable): + new_stride = b - a + if stride is None: + stride = new_stride + elif stride != new_stride: + return None + return stride + +def minmax(iterable): + """Return the minimum and maximum of an iterable series. + + This function requires only a single pass over the data. + + Args: + iterable: An iterable series for which to determine the minimum and + maximum values. + + Returns: + A 2-tuple containing the minimum and maximum values. + """ + iterator = iter(iterable) + try: + first = next(iterator) + except StopIteration: + raise ValueError("minmax() arg is an empty iterable series") + minimum = first + maximum = first + for item in iterator: + minimum = min(minimum, item) + maximum = max(maximum, item) + return minimum, maximum + + +def file_length(fh): + """Determine the length of a file-like object in bytes. + + Args: + fh: A seekable file-like-object. + + Returns: + An integer length in bytes. + """ + pos = fh.tell() + try: + fh.seek(0, os.SEEK_END) + return fh.tell() + finally: + fh.seek(pos, os.SEEK_SET) + + +def filename_from_handle(fh): + """Determine the name of the file underlying a file-like object. + + Args: + fh: A file-like object. + + Returns: + A string containing the file name, or '' if it could not + be determined. + """ + try: + return fh.name + except AttributeError: + return '' + + +def now_millis(): + millis = int(round(time.time() * 1000)) + return millis + + +def round_up(integer, multiple): + """Round up to the nearest multiple""" + return integer if integer % multiple == 0 else integer + multiple - integer % multiple + + +def underscores_to_camelcase(s): + """Convert text_in_this_style to TextInThisStyle.""" + return ''.join(w.capitalize() for w in s.split('_')) + + +def almost_equal(x, y, epsilon): + max_xy_one = max(1.0, abs(x), abs(y)) + e = epsilon * max_xy_one + delta = abs(x - y) + return delta <= e \ No newline at end of file diff --git a/segpy/writer.py b/segpy/writer.py new file mode 100644 index 0000000..db97d69 --- /dev/null +++ b/segpy/writer.py @@ -0,0 +1,58 @@ +from segpy.encoding import ASCII, is_supported_encoding, UnsupportedEncodingError +from segpy.toolkit import (write_textual_reel_header, write_binary_reel_header, compile_trace_header_format, + write_trace_header, write_trace_samples, format_extended_textual_header, + write_extended_textual_headers) + + +def write_segy(fh, + seg_y_data, + encoding=None, + endian='>', + progress=None): + """ + Args: + fh: A file-like object open for binary write. + + seg_y_data: An object from which the headers and trace_samples data can be retrieved. Requires the following + properties and methods: + seg_y_data.textual_reel_header + seg_y_data.binary_reel_header + seg_y_data.extended_textual_header + seg_y_data.trace_indexes + seg_y_data.trace_header(trace_index) + seg_y_data.trace_samples(trace_index) + + seg_y_data.encoding + seg_y_data.endian + + One such legitimate object would be a SegYReader instance. + + encoding: Optional encoding for text data. Typically 'cp037' for EBCDIC or 'ascii' for ASCII. If omitted, the + seg_y_data object will be queries for an encoding property. + + endian: Big endian by default. If omitted, the seg_y_data object will be queried for an encoding property. + + progress: An optional progress bar object. + + Raises: + UnsupportedEncodingError: If the specified encoding is neither ASCII nor EBCDIC + UnicodeError: If textual data provided cannot be encoded into the required encoding. + """ + + encoding = encoding or (hasattr(seg_y_data, 'encoding') and seg_y_data.encoding) or ASCII + + if not is_supported_encoding(encoding): + raise UnsupportedEncodingError("Writing SEG Y", encoding) + + write_textual_reel_header(fh, seg_y_data.textual_reel_header, encoding) + write_binary_reel_header(fh, seg_y_data.binary_reel_header, endian) + write_extended_textual_headers(fh, seg_y_data.extended_textual_header, encoding) + + trace_header_format = compile_trace_header_format(endian) + + for trace_index in seg_y_data.trace_indexes(): + write_trace_header(fh, seg_y_data.trace_header(trace_index), trace_header_format) + write_trace_samples(fh, seg_y_data.trace_samples(trace_index), seg_y_data.data_sample_format, endian=endian) + + + diff --git a/segypy.py b/segypy.py deleted file mode 100644 index 4a01ce2..0000000 --- a/segypy.py +++ /dev/null @@ -1,511 +0,0 @@ -""" -A Python module for reading/writing/manipulating -SEG-Y formatted files - -segy.readSegy : Read SEGY file -segy.read_reel_header : Get SEGY header -segy.read_trace_header : Get SEGY Trace header -segy.read_all_trace_headers : Get all SEGY Trace headers -segy.getSegyTrace : Get SEGY Trace header and trace data for one trace - -segy.writeSegy : Write a data to a SEGY file -segy.writeSegyStructure : Writes a segpy data structure to a SEGY file - -segy.read_binary_value : Get a value from a binary string -segy.ibm2ieee : Convert IBM floats to IEEE - -segy.version : The version of SegyPY -segy.verbose : Amount of verbose information to the screen -""" -# -# segpy : A Python module for reading and writing SEG-Y formatted data -# -# Forked by Robert Smallshire from the original segypy by -# -# (C) Thomas Mejer Hansen, 2005-2006 -# -# with contributions from Pete Forman and Andrew Squelch 2007 -import os - -import sys -import struct -import logging - -from numpy import (transpose, reshape, zeros, arange) - -from revisions import canonicalize_revision -from header_definition import HEADER_DEF -from trace_header_definition import TRACE_HEADER_DEF -from ibm_float import ibm2ieee2 - -FORMAT = '%(asctime)-15s %(levelname)s %(message)s' -logging.basicConfig(level=logging.INFO, format=FORMAT) -logger = logging.getLogger('segpy.segypy') - -version = '0.3.1' - -REEL_HEADER_NUM_BYTES = 3600 -TRACE_HEADER_NUM_BYTES = 240 - -l_char = struct.calcsize('c') -l_uchar = struct.calcsize('B') -l_float = struct.calcsize('f') - - -DATA_SAMPLE_FORMAT = {1: 'ibm', - 2: 'l', - 3: 'h', - 5: 'f', - 8: 'B'} - -CTYPES = {'l': 'l', 'long': 'l', 'int32': 'l', - 'L': 'L', 'ulong': 'L', 'uint32': 'L', - 'h': 'h', 'short': 'h', 'int16': 'h', - 'H': 'H', 'ushort': 'H', 'uint16': 'H', - 'c': 'c', 'char': 'c', - 'B': 'B', 'uchar': 'B', - 'f': 'f', 'float': 'f', - 'ibm': 'ibm'} - -# TODO This is redundant with data in the SH_def below -CTYPE_DESCRIPTION = {'ibm': 'IBM float', - 'l': '32 bit integer', - 'h': '16 bit integer', - 'f': 'IEEE float', - 'B': '8 bit char'} - - -def size_in_bytes(ctype): - if ctype == 'l' and struct.calcsize(ctype) == 8: - return 4 # 64-bit issue? - return struct.calcsize(ctype) if ctype != 'ibm' else struct.calcsize('f') - - -def get_default_segy_header(ntraces=100, ns=100): - """ - header = getDefaultSegyHeader() - """ - # TraceSequenceLine - header = {'Job': {'pos': 3200, 'type': 'int32', 'def': 0}} - - for key in HEADER_DEF: - header[key] = HEADER_DEF[key].get('def', 0) - - header['ntraces'] = ntraces - header['ns'] = ns - - return header - - -def get_default_segy_trace_headers(ntraces=100, ns=100, dt=1000): - """ - SH = getDefaultSegyTraceHeader() - """ - # INITIALIZE DICTIONARY - trace_header = {'TraceSequenceLine': {'pos': 0, 'type': 'int32'}} - - for key in TRACE_HEADER_DEF: - trace_header[key] = zeros(ntraces) - - for a in range(ntraces): - trace_header['TraceSequenceLine'][a] = a + 1 - trace_header['TraceSequenceFile'][a] = a + 1 - trace_header['FieldRecord'][a] = 1000 - trace_header['TraceNumber'][a] = a + 1 - trace_header['ns'][a] = ns - trace_header['dt'][a] = dt - return trace_header - - -def read_trace_header(f, reel_header, trace_header_name='cdp', endian='>'): - """ - read_trace_header(reel_header, TraceHeaderName) - """ - - bps = get_byte_per_sample(reel_header) - - # MAKE SOME LOOKUP TABLE THAT HOLDS THE LOCATION OF HEADERS - trace_header_pos = TRACE_HEADER_DEF[trace_header_name]['pos'] - - # TODO: Be consistent between 'type' and 'format' here. - trace_header_format = TRACE_HEADER_DEF[trace_header_name]['type'] - ntraces = reel_header['ntraces'] - trace_header_values = zeros(ntraces) - binary_reader = create_binary_reader(f, trace_header_format, endian) - start_pos = trace_header_pos + REEL_HEADER_NUM_BYTES - stride = reel_header['ns'] * bps + TRACE_HEADER_NUM_BYTES - end_pos = start_pos + (ntraces - 1) * stride + 1 - for i, pos in enumerate(xrange(start_pos, end_pos, stride)): - trace_header_values[i] = binary_reader(pos) - return trace_header_values - - -# TODO: Get the parameter ordering of reel_header and f to be consistent -def read_all_trace_headers(f, reel_header): - trace_headers = {'filename': reel_header['filename']} - - logger.debug('read_all_trace_headers : ' - 'trying to get all segy trace headers') - - for key in TRACE_HEADER_DEF.keys(): - trace_header = read_trace_header(f, reel_header, key) - trace_headers[key] = trace_header - logger.info("read_all_trace_headers : " + key) - - return trace_headers - - -def file_length(f): - pos = f.tell() - f.seek(0, os.SEEK_END) - file_size = f.tell() - f.seek(pos, os.SEEK_SET) - return file_size - - -def _filename(f): - return f.name if hasattr(f, 'name') else '' - - -def read_segy(f, endian='>'): - """ - data, header, trace_headers = read_reel_header(f) - """ - - file_size = file_length(f) - - logger.debug("read_segy : Length of data : {0}".format(file_size)) - - reel_header = read_reel_header(f, endian) # modified by A Squelch - - # GET TRACE - index = REEL_HEADER_NUM_BYTES - bytes_per_sample = get_byte_per_sample(reel_header) - num_data = (file_size - REEL_HEADER_NUM_BYTES) / bytes_per_sample - - data, reel_header, trace_headers = read_traces(f, - reel_header, - num_data, - bytes_per_sample, - index, - endian) - - logger.debug("read_segy : Read segy data") # modified by A Squelch - - return data, reel_header, trace_headers - - -def read_traces(f, - reel_header, - num_data, - bytes_per_sample, - index, - endian='>'): # added by A Squelch - """Read the trace data. - - values, SegyHeader, SegyTraceHeaders = read_traces(data, - reel_header, - num_data, - bytes_per_sample, - index) - """ - - # Calculate number of dummy samples needed to account for Trace Headers - num_dummy_samples = TRACE_HEADER_NUM_BYTES / bytes_per_sample - logger.debug("read_traces : num_dummy_samples = " + str(num_dummy_samples)) - - # READ ALL SEGY TRACE HEADERS - trace_headers = read_all_trace_headers(f, reel_header) - - logger.info("read_traces : Reading segy data") - - dsf = reel_header['DataSampleFormat'] - ctype = DATA_SAMPLE_FORMAT[dsf] - description = CTYPE_DESCRIPTION[ctype] - logger.debug("read_traces : Assuming DSF = {0}, {1}".format( - dsf, description)) - values, _ = read_binary_value(f, index, ctype, endian, num_data) - - logger.debug("read_traces : - reshaping") - values = reshape(values, - (reel_header['ntraces'], - reel_header['ns'] + num_dummy_samples)) - logger.debug("read_traces : - stripping header dummy data") - values = values[:, num_dummy_samples: - (reel_header['ns'] + num_dummy_samples)] - logger.debug("read_traces : - transposing") - values = transpose(values) - - # SOMEONE NEEDS TO IMPLEMENT A NICER WAY DO DEAL WITH DSF = 8 - if reel_header['DataSampleFormat'] == 8: - for i in arange(reel_header['ntraces']): - for j in arange(reel_header['ns']): - if values[i][j] > 128: - values[i][j] = values[i][j] - 256 - - logger.debug("read_traces : Finished reading segy data") - - return values, reel_header, trace_headers - - -def read_reel_header(f, endian='>'): - """ - reel_header = read_reel_header(file_handle) - """ - filename = _filename(f) - reel_header = {'filename': filename} - for key in HEADER_DEF.keys(): - pos = HEADER_DEF[key]['pos'] - format = HEADER_DEF[key]['type'] - - reel_header[key], index = read_binary_value(f, pos, format, endian) - - logger.debug(str(pos) + " " + - str(format) + - " Reading " + key + - "=" + str(reel_header[key])) - - # SET NUMBER OF BYTES PER DATA SAMPLE - bps = get_byte_per_sample(reel_header) - - file_size = file_length(f) - ntraces = (file_size - REEL_HEADER_NUM_BYTES) / \ - (reel_header['ns'] * bps + TRACE_HEADER_NUM_BYTES) - reel_header['ntraces'] = ntraces - - logger.debug('read_reel_header : successfully read ' + filename) - - return reel_header - - -def write_segy(filename, data, dt=1000, trace_header_in=None, header_in=None): - """ - write_segy(filename, data, dt) - - Write SEGY - - See also read_segy - - (c) 2005, Thomas Mejer Hansen - - MAKE OPTIONAL INPUT FOR ALL SEGYHTRACEHEADER VALUES - - """ - if header_in is None: - header_in = {} - if trace_header_in is None: - trace_header_in = {} - - logger.debug("write_segy : Trying to write " + filename) - - shape = data.shape - ns = shape[0] - ntraces = shape[1] - print ntraces, ns - - header = get_default_segy_header(ntraces, ns) - trace_header = get_default_segy_trace_headers(ntraces, ns, dt) - - # Add trace_header_in, if exists... - for key in trace_header_in.keys(): - print key - for a in range(ntraces): - trace_header[key] = trace_header_in[key][a] - - # Add header_in, if exists... - for key in header_in.keys(): - print key - header[key] = header_in[key] - - write_segy_structure(filename, data, header, trace_header) - - -def write_segy_structure(filename, - data, - header, - trace_header, - endian='>'): # modified by A Squelch - """ - writeSegyStructure(filename, data, header, trace_header) - - Write SEGY file using SegyPy data structures - - See also readSegy - - (c) 2005, Thomas Mejer Hansen - - """ - - logger.debug("writeSegyStructure : Trying to write " + filename) - - f = open(filename, 'wb') - - # VERBOSE INF - revision = canonicalize_revision(header['SegyFormatRevisionNumber']) - dsf = header['DataSampleFormat'] - - try: # block added by A Squelch - data_descriptor = HEADER_DEF['DataSampleFormat']['descr'][revision][dsf] - except KeyError: - logging.critical(" An error has occurred interpreting a SEGY binary" - "header key") - logging.critical(" Please check the Endian setting for this " - "file: {0}".format(header["filename"])) - sys.exit() - - logger.debug("writeSegyStructure : SEG-Y revision = " + str(revision)) - logger.debug("writeSegyStructure : DataSampleFormat = " + - str(dsf) + - "(" + data_descriptor + ")") - - # WRITE SEGY HEADER - - for key in HEADER_DEF.keys(): - pos = HEADER_DEF[key]["pos"] - format = HEADER_DEF[key]["type"] - value = header[key] - put_value(value, f, pos, format, endian) - - # SEGY TRACES - ctype = HEADER_DEF['DataSampleFormat']['datatype'][revision][dsf] - bps = HEADER_DEF['DataSampleFormat']['bps'][revision][dsf] - - sizeT = TRACE_HEADER_NUM_BYTES + header['ns'] * bps - - for itrace in range(header['ntraces']): - index = REEL_HEADER_NUM_BYTES + itrace * sizeT - logger.debug('Writing Trace #' + - str(itrace + 1) + - '/' + str(header['ntraces'])) - # WRITE SEGY TRACE HEADER - for key in TRACE_HEADER_DEF.keys(): - pos = index + TRACE_HEADER_DEF[key]['pos'] - format = TRACE_HEADER_DEF[key]['type'] - value = trace_header[key][itrace] - logger.debug(str(pos) + " " + - str(format) + - " Writing " + key + - "=" + str(value)) - put_value(value, f, pos, format, endian) - - # Write Data - cformat = endian + ctype - for s in range(header['ns']): - strVal = struct.pack(cformat, data[s, itrace]) - f.seek(index + - TRACE_HEADER_NUM_BYTES + - s * struct.calcsize(cformat)) - f.write(strVal) - - f.close() - - -def put_value(value, fileid, index, ctype='l', endian='>', number=1): - """ - putValue(data, index, ctype, endian, number) - """ - ctype = CTYPES[ctype] - - cformat = endian + ctype*number - - logger.debug('putValue : cformat : ' + cformat + ' ctype = ' + ctype) - - str_val = struct.pack(cformat, value) - fileid.seek(index) - fileid.write(str_val) - - return 1 - - -def create_binary_reader(f, ctype='l', endian='>'): - """Create a unary callable which reads a given binary data type from a file. - """ - ctype = CTYPES[ctype] - size = size_in_bytes(ctype) - - cformat = endian + ctype - - def reader(index): - f.seek(index, os.SEEK_SET) - data = f.read(size) - # TODO: Check the content of data before proceeding - value = struct.unpack(cformat, data) - return value[0] - - return reader - - -def read_binary_value(f, index, ctype='l', endian='>', number=1): - """ - read_binary_value(data, index, ctype, endian, number) - """ - - ctype = CTYPES[ctype] - - size = size_in_bytes(ctype) - - cformat = endian + ctype * number - - logger.debug('read_binary_value : cformat : ' + cformat) - - index_end = index + size * number - - f.seek(index, os.SEEK_SET) - data = f.read(size * number) - if ctype == 'ibm': - # ASSUME IBM FLOAT DATA - value = range(number) - for i in arange(number): - index_ibm = i * 4 - value[i] = ibm2ieee2(data[index_ibm: index_ibm + 4]) - # this returns an array as opposed to a tuple - else: - # TODO: Check the content of data before proceeding - value = struct.unpack(cformat, data) - - if ctype == 'B': - logger.warning('read_binary_value : ' - 'Inefficient use of 1 byte Integer...', 1) - - logger.debug('read_binary_value : ' + - 'start = ' + str(index) + - ' size = ' + str(size) + - ' number = ' + str(number) + - ' value = ' + str(value) + - ' cformat = ' + str(cformat)) - - if number == 1: - return value[0], index_end - else: - return value, index_end - - -def get_byte_per_sample(header): - revision = canonicalize_revision(header["SegyFormatRevisionNumber"]) - dsf = header["DataSampleFormat"] - - try: # block added by A Squelch - bps = HEADER_DEF["DataSampleFormat"]["bps"][revision][dsf] - except KeyError: - # TODO: This should not be a critical failure - should just convert - # exception - logging.critical(" An error has occurred interpreting a SEGY " - "binary header key") - logging.critical("Please check the Endian setting for " - "this file: {0}".format(header["filename"])) - sys.exit() - - logger.debug("getBytePerSample : bps = " + str(bps)) - - return bps - - -def main(): - filename = r'C:\Users\rjs\opendtectroot\Blake_Ridge_Hydrates_3D' \ - r'\stack_final_scaled50_int8.sgy' - with open(filename, 'rb') as segy: - data, header, trace_header = read_segy(segy) - - -if __name__ == '__main__': - main() diff --git a/setup.cfg b/setup.cfg new file mode 100644 index 0000000..79bc678 --- /dev/null +++ b/setup.cfg @@ -0,0 +1,5 @@ +[bdist_wheel] +# This flag says that the code is written to work on both Python 2 and Python +# 3. If at all possible, it is good practice to do this. If you cannot, you +# will need to generate wheels for each Python version that you support. +universal=1 diff --git a/setup.py b/setup.py new file mode 100644 index 0000000..cb1e41d --- /dev/null +++ b/setup.py @@ -0,0 +1,119 @@ +import io +import os +import re +from setuptools import setup, find_packages # Always prefer setuptools over distutils +from codecs import open # To use a consistent encoding +from os import path + + +def read(*names, **kwargs): + with io.open( + os.path.join(os.path.dirname(__file__), *names), + encoding=kwargs.get("encoding", "utf8") + ) as fp: + return fp.read() + + +def find_version(*file_paths): + version_file = read(*file_paths) + version_match = re.search(r"^__version__ = ['\"]([^'\"]*)['\"]", + version_file, re.M) + if version_match: + return version_match.group(1) + raise RuntimeError("Unable to find version string.") + + +here = path.abspath(path.dirname(__file__)) + +# Get the long description from the relevant file +with open(path.join(here, 'DESCRIPTION.rst'), encoding='utf-8') as f: + long_description = f.read() + +setup( + name='segpy', + + # Versions should comply with PEP440. For a discussion on single-sourcing + # the version across setup.py and the project code, see + # https://packaging.python.org/en/latest/single_source_version.html + version=find_version("segpy/__init__.py"), + + description='Transfer of seismic data to and from SEG Y files', + long_description=long_description, + + # The project's main homepage. + url='https://github.com/rob-smallshire/segpy', + + # Author details + author='Robert Smallshire', + author_email='robert@smallshire.org.uk', + + # Choose your license + license='GPL', + + # See https://pypi.python.org/pypi?%3Aaction=list_classifiers + classifiers=[ + # How mature is this project? Common values are + # 3 - Alpha + # 4 - Beta + # 5 - Production/Stable + 'Development Status :: 3 - Alpha', + + # Indicate who your project is intended for + 'Intended Audience :: Developers', + 'Topic :: Scientific/Engineering', + 'Topic :: Software Development :: Libraries', + + # Pick your license as you wish (should match "license" above) + 'License :: OSI Approved :: MIT License', + + # Specify the Python versions you support here. In particular, ensure + # that you indicate whether you support Python 2, Python 3 or both. + 'Programming Language :: Python :: 2.7', + 'Programming Language :: Python :: 3', + 'Programming Language :: Python :: 3.3', + 'Programming Language :: Python :: 3.4', + ], + + # What does your project relate to? + keywords='seismic geocomputing geophysics', + + # You can just specify the packages manually here if your project is + # simple. Or you can use find_packages(). + packages=find_packages(exclude=['contrib', 'docs', 'test*']), + + # List run-time dependencies here. These will be installed by pip when your + # project is installed. For an analysis of "install_requires" vs pip's + # requirements files see: + # https://packaging.python.org/en/latest/requirements.html + install_requires=[], + + # List additional groups of dependencies here (e.g. development dependencies). + # You can install these using the following syntax, for example: + # $ pip install -e .[dev,test] + extras_require = { + 'dev': ['check-manifest', 'wheel'], + 'doc': ['sphinx', 'cartouche'], + 'test': ['coverage', 'hypothesis'], + }, + + # If there are data files included in your packages that need to be + # installed, specify them here. If using Python 2.6 or less, then these + # have to be included in MANIFEST.in as well. + package_data={ + }, + + # Although 'package_data' is the preferred approach, in some case you may + # need to place data files outside of your packages. + # see http://docs.python.org/3.4/distutils/setupscript.html#installing-additional-files + # In this case, 'data_file' will be installed into '/my_data' + data_files=[], + + # To provide executable scripts, use entry points in preference to the + # "scripts" keyword. Entry points provide cross-platform support and allow + # pip to create the appropriate form of executable for the target platform. + entry_points={ + 'console_scripts': [ + ], + }, +) + diff --git a/test/__init__.py b/test/__init__.py new file mode 100644 index 0000000..8b13789 --- /dev/null +++ b/test/__init__.py @@ -0,0 +1 @@ + diff --git a/test/strategies.py b/test/strategies.py new file mode 100644 index 0000000..c56725d --- /dev/null +++ b/test/strategies.py @@ -0,0 +1,21 @@ +from hypothesis import strategy +from hypothesis.specifiers import integers_in_range + +PRINTABLE_ASCII_RANGE = (32, 127) + + +def multiline_ascii_encodable_text(min_num_lines, max_num_lines): + """A Hypothesis strategy to produce a multiline Unicode string. + + Args: + min_num_lines: The minimum number of lines in the produced strings. + max_num_lines: The maximum number of lines in the produced strings. + + Returns: + A strategy for generating Unicode strings containing only newlines + and characters which are encodable as printable 7-bit ASCII characters. + """ + + return strategy(integers_in_range(0, 10)) \ + .flatmap(lambda n: ([integers_in_range(*PRINTABLE_ASCII_RANGE)],) * n) \ + .map(lambda xs: '\n'.join(bytes(x).decode('ascii') for x in xs)) diff --git a/test/test-requirements.txt b/test/test-requirements.txt new file mode 100644 index 0000000..bcf2f58 --- /dev/null +++ b/test/test-requirements.txt @@ -0,0 +1 @@ +hypothesis>=1.2 diff --git a/test/test_extended_textual_header.py b/test/test_extended_textual_header.py new file mode 100644 index 0000000..99cd2cd --- /dev/null +++ b/test/test_extended_textual_header.py @@ -0,0 +1,41 @@ +import unittest +from hypothesis import given +from hypothesis.specifiers import sampled_from, just +from segpy.encoding import EBCDIC, ASCII +from segpy.toolkit import format_extended_textual_header, CARDS_PER_HEADER, END_TEXT_STANZA, CARD_LENGTH +from test.strategies import multiline_ascii_encodable_text + + +class TestFormatExtendedTextualHeader(unittest.TestCase): + + @given(multiline_ascii_encodable_text(0, 100), + sampled_from([ASCII, EBCDIC]), + bool) + def test_forty_lines_per_page(self, text, encoding, include_text_stop): + pages = format_extended_textual_header(text, encoding, include_text_stop) + self.assertTrue(all(len(page) == CARDS_PER_HEADER for page in pages)) + + @given(multiline_ascii_encodable_text(0, 100), + sampled_from([ASCII, EBCDIC]), + bool) + def test_eighty_bytes_per_encoded_line(self, text, encoding, include_text_stop): + pages = format_extended_textual_header(text, encoding, include_text_stop) + self.assertTrue(all([len(line.encode(encoding)) == CARD_LENGTH for page in pages for line in page])) + + @given(multiline_ascii_encodable_text(0, 100), + sampled_from([ASCII, EBCDIC]), + bool) + def test_lines_end_with_cr_lf(self, text, encoding, include_text_stop): + pages = format_extended_textual_header(text, encoding, include_text_stop) + self.assertTrue(all([line.endswith('\r\n') for page in pages for line in page])) + + @given(multiline_ascii_encodable_text(0, 100), + sampled_from([ASCII, EBCDIC]), + just(True)) + def test_end_text_stanza_present(self, text, encoding, include_text_stop): + pages = format_extended_textual_header(text, encoding, include_text_stop) + self.assertTrue(pages[-1][0].startswith(END_TEXT_STANZA)) + + +if __name__ == '__main__': + unittest.main() \ No newline at end of file diff --git a/test/test_float.py b/test/test_float.py new file mode 100644 index 0000000..e345b87 --- /dev/null +++ b/test/test_float.py @@ -0,0 +1,364 @@ +from math import trunc, floor +import unittest + +from hypothesis import given, assume +import math +from hypothesis.specifiers import integers_in_range, floats_in_range + +from segpy.portability import byte_string +from segpy.ibm_float import (ieee2ibm, ibm2ieee, MAX_IBM_FLOAT, SMALLEST_POSITIVE_NORMAL_IBM_FLOAT, + LARGEST_NEGATIVE_NORMAL_IBM_FLOAT, MIN_IBM_FLOAT, IBMFloat, EPSILON_IBM_FLOAT, + MAX_EXACT_INTEGER_IBM_FLOAT, MIN_EXACT_INTEGER_IBM_FLOAT, EXPONENT_BIAS) +from segpy.util import almost_equal + + +class Ibm2Ieee(unittest.TestCase): + + def test_zero(self): + self.assertEqual(ibm2ieee(b'\0\0\0\0'), 0.0) + + def test_positive_half(self): + self.assertEqual(ibm2ieee(byte_string((0b11000000, 0x80, 0x00, 0x00))), -0.5) + + def test_negative_half(self): + self.assertEqual(ibm2ieee(byte_string((0b01000000, 0x80, 0x00, 0x00))), 0.5) + + def test_one(self): + self.assertEqual(ibm2ieee(b'\x41\x10\x00\x00'), 1.0) + + def test_negative_118_625(self): + # Example taken from Wikipedia http://en.wikipedia.org/wiki/IBM_Floating_Point_Architecture + self.assertEqual(ibm2ieee(byte_string((0b11000010, 0b01110110, 0b10100000, 0b00000000))), -118.625) + + def test_largest_representable_number(self): + self.assertEqual(ibm2ieee(byte_string((0b01111111, 0b11111111, 0b11111111, 0b11111111))), MAX_IBM_FLOAT) + + def test_smallest_positive_normalised_number(self): + self.assertEqual(ibm2ieee(byte_string((0b00000000, 0b00010000, 0b00000000, 0b00000000))), SMALLEST_POSITIVE_NORMAL_IBM_FLOAT) + + def test_largest_negative_normalised_number(self): + self.assertEqual(ibm2ieee(byte_string((0b10000000, 0b00010000, 0b00000000, 0b00000000))), LARGEST_NEGATIVE_NORMAL_IBM_FLOAT) + + def test_smallest_representable_number(self): + self.assertEqual(ibm2ieee(byte_string((0b11111111, 0b11111111, 0b11111111, 0b11111111))), MIN_IBM_FLOAT) + + def test_error_1(self): + self.assertEqual(ibm2ieee(byte_string((196, 74, 194, 143))), -19138.55859375) + + def test_error_2(self): + self.assertEqual(ibm2ieee(byte_string((191, 128, 0, 0))), -0.03125) + + def test_subnormal(self): + self.assertEqual(ibm2ieee(byte_string((0x00, 0x00, 0x00, 0x20))), 1.6472184286297693e-83) + + def test_subnormal_is_subnormal(self): + self.assertTrue(0 < ibm2ieee(byte_string((0x00, 0x00, 0x00, 0x20))) < SMALLEST_POSITIVE_NORMAL_IBM_FLOAT) + + def test_subnormal_smallest_subnormal(self): + self.assertEqual(ibm2ieee(byte_string((0x00, 0x00, 0x00, 0x01))), 5.147557589468029e-85) + + +class Ieee2Ibm(unittest.TestCase): + + def test_zero(self): + self.assertEqual(ieee2ibm(0.0), b'\0\0\0\0') + + def test_positive_half(self): + self.assertEqual(ieee2ibm(-0.5), byte_string((0b11000000, 0x80, 0x00, 0x00))) + + def test_negative_half(self): + self.assertEqual(ieee2ibm(0.5), byte_string((0b01000000, 0x80, 0x00, 0x00))) + + def test_one(self): + self.assertEqual(ieee2ibm(1.0), b'\x41\x10\x00\x00') + + def test_negative_118_625(self): + # Example taken from Wikipedia http://en.wikipedia.org/wiki/IBM_Floating_Point_Architecture + self.assertEqual(ieee2ibm(-118.625), byte_string((0b11000010, 0b01110110, 0b10100000, 0b00000000))) + + def test_0_1(self): + # Note, this is different from the Wikipedia example, because the Wikipedia example does + # round to nearest, and our routine does round to zero + self.assertEqual(ieee2ibm(0.1), byte_string((0b01000000, 0b00011001, 0b10011001, 0b10011001))) + + def test_subnormal(self): + self.assertEqual(ieee2ibm(1.6472184286297693e-83), byte_string((0x00, 0x00, 0x00, 0x20))) + + def test_smallest_subnormal(self): + self.assertEqual(ieee2ibm(5.147557589468029e-85), byte_string((0x00, 0x00, 0x00, 0x01))) + + def test_too_small_subnormal(self): + with self.assertRaises(FloatingPointError): + ieee2ibm(1e-86) + + def test_nan(self): + with self.assertRaises(ValueError): + ieee2ibm(float('nan')) + + def test_inf(self): + with self.assertRaises(ValueError): + ieee2ibm(float('inf')) + + def test_too_large(self): + with self.assertRaises(OverflowError): + ieee2ibm(MAX_IBM_FLOAT * 10) + + def test_too_small(self): + with self.assertRaises(OverflowError): + ieee2ibm(MIN_IBM_FLOAT * 10) + + +class Ibm2IeeeRoundtrip(unittest.TestCase): + + def test_zero(self): + ibm_start = b'\0\0\0\0' + f = ibm2ieee(ibm_start) + ibm_result = ieee2ibm(f) + self.assertEqual(ibm_start, ibm_result) + + def test_positive_half(self): + ibm_start = byte_string((0b11000000, 0x80, 0x00, 0x00)) + f = ibm2ieee(ibm_start) + ibm_result = ieee2ibm(f) + self.assertEqual(ibm_start, ibm_result) + + def test_negative_half(self): + ibm_start = byte_string((0b01000000, 0x80, 0x00, 0x00)) + f = ibm2ieee(ibm_start) + ibm_result = ieee2ibm(f) + self.assertEqual(ibm_start, ibm_result) + + def test_one(self): + ibm_start = b'\x41\x10\x00\x00' + f = ibm2ieee(ibm_start) + ibm_result = ieee2ibm(f) + self.assertEqual(ibm_start, ibm_result) + + def test_subnormal(self): + ibm_start = byte_string((0x00, 0x00, 0x00, 0x20)) + f = ibm2ieee(ibm_start) + ibm_result = ieee2ibm(f) + self.assertEqual(ibm_start, ibm_result) + + +class TestIBMFloat(unittest.TestCase): + + def test_zero_from_float(self): + zero = IBMFloat.from_float(0.0) + self.assertTrue(zero.is_zero()) + + def test_zero_from_bytes(self): + zero = IBMFloat.from_bytes(b'\x00\x00\x00\x00') + self.assertTrue(zero.is_zero()) + + def test_subnormal(self): + ibm = IBMFloat.from_float(1.6472184286297693e-83) + self.assertTrue(ibm.is_subnormal()) + + def test_smallest_subnormal(self): + ibm = IBMFloat.from_float(5.147557589468029e-85) + self.assertEqual(bytes(ibm), byte_string((0x00, 0x00, 0x00, 0x01))) + + def test_too_small_subnormal(self): + with self.assertRaises(FloatingPointError): + IBMFloat.from_float(1e-86) + + def test_nan(self): + with self.assertRaises(ValueError): + IBMFloat.from_float(float('nan')) + + def test_inf(self): + with self.assertRaises(ValueError): + IBMFloat.from_float(float('inf')) + + def test_too_large(self): + with self.assertRaises(OverflowError): + IBMFloat.from_float(MAX_IBM_FLOAT * 10) + + def test_too_small(self): + with self.assertRaises(OverflowError): + IBMFloat.from_float(MIN_IBM_FLOAT * 10) + + @given(floats_in_range(MIN_IBM_FLOAT, MAX_IBM_FLOAT)) + def test_bool(self, f): + self.assertEqual(bool(IBMFloat.from_float(f)), bool(f)) + + @given(integers_in_range(0, 255), + integers_in_range(0, 255), + integers_in_range(0, 255), + integers_in_range(0, 255)) + def test_bytes_roundtrip(self, a, b, c, d): + b = byte_string((a, b, c, d)) + ibm = IBMFloat.from_bytes(b) + self.assertEqual(bytes(ibm), b) + + @given(floats_in_range(MIN_IBM_FLOAT, MAX_IBM_FLOAT)) + def test_floats_roundtrip(self, f): + ibm = IBMFloat.from_float(f) + self.assertTrue(almost_equal(f, float(ibm), epsilon=EPSILON_IBM_FLOAT)) + + @given(integers_in_range(0, MAX_EXACT_INTEGER_IBM_FLOAT - 1), + floats_in_range(0.0, 1.0)) + def test_trunc_above_zero(self, i, f): + assume(f != 1.0) + ieee = i + f + ibm = IBMFloat.from_float(ieee) + self.assertEqual(trunc(ibm), i) + + @given(integers_in_range(MIN_EXACT_INTEGER_IBM_FLOAT + 1, 0), + floats_in_range(0.0, 1.0)) + def test_trunc_below_zero(self, i, f): + assume(f != 1.0) + ieee = i - f + ibm = IBMFloat.from_float(ieee) + self.assertEqual(trunc(ibm), i) + + @given(integers_in_range(MIN_EXACT_INTEGER_IBM_FLOAT, MAX_EXACT_INTEGER_IBM_FLOAT - 1), + floats_in_range(0.0, 1.0)) + def test_ceil(self, i, f): + assume(f != 1.0) + ieee = i + f + ibm = IBMFloat.from_float(ieee) + self.assertEqual(math.ceil(ibm), i + 1) + + @given(integers_in_range(MIN_EXACT_INTEGER_IBM_FLOAT, MAX_EXACT_INTEGER_IBM_FLOAT - 1), + floats_in_range(0.0, 1.0)) + def test_floor(self, i, f): + assume(f != 1.0) + ieee = i + f + ibm = IBMFloat.from_float(ieee) + self.assertEqual(math.floor(ibm), i) + + def test_normalise_subnormal_expect_failure(self): + # This float has an base-16 exponent of -64 (the minimum) and cannot be normalised + ibm = IBMFloat.from_float(1.6472184286297693e-83) + assert ibm.is_subnormal() + with self.assertRaises(FloatingPointError): + ibm.normalize() + + def test_normalise_subnormal1(self): + ibm = IBMFloat.from_bytes((0b01000000, 0b00000000, 0b11111111, 0b00000000)) + assert ibm.is_subnormal() + normalized = ibm.normalize() + self.assertFalse(normalized.is_subnormal()) + + def test_normalise_subnormal2(self): + ibm = IBMFloat.from_bytes((64, 1, 0, 0)) + assert ibm.is_subnormal() + normalized = ibm.normalize() + self.assertFalse(normalized.is_subnormal()) + + @given(integers_in_range(128, 255), + integers_in_range(0, 255), + integers_in_range(0, 255), + integers_in_range(4, 23)) + def test_normalise_subnormal(self, b, c, d, shift): + mantissa = (b << 16) | (c << 8) | d + assume(mantissa != 0) + mantissa >>= shift + assert mantissa != 0 + + sa = EXPONENT_BIAS + sb = (mantissa >> 16) & 0xff + sc = (mantissa >> 8) & 0xff + sd = mantissa & 0xff + + ibm = IBMFloat.from_bytes((sa, sb, sc, sd)) + assert ibm.is_subnormal() + normalized = ibm.normalize() + self.assertFalse(normalized.is_subnormal()) + + @given(integers_in_range(128, 255), + integers_in_range(0, 255), + integers_in_range(0, 255), + integers_in_range(4, 23)) + def test_zero_subnormal(self, b, c, d, shift): + mantissa = (b << 16) | (c << 8) | d + assume(mantissa != 0) + mantissa >>= shift + assert mantissa != 0 + + sa = EXPONENT_BIAS + sb = (mantissa >> 16) & 0xff + sc = (mantissa >> 8) & 0xff + sd = mantissa & 0xff + + ibm = IBMFloat.from_bytes((sa, sb, sc, sd)) + assert ibm.is_subnormal() + z = ibm.zero_subnormal() + self.assertTrue(z.is_zero()) + + @given(integers_in_range(0, 255), + integers_in_range(0, 255), + integers_in_range(0, 255), + integers_in_range(0, 255)) + def test_abs(self, a, b, c, d): + ibm = IBMFloat.from_bytes((a, b, c, d)) + abs_ibm = abs(ibm) + self.assertGreaterEqual(abs_ibm.signbit, 0) + + @given(integers_in_range(0, 255), + integers_in_range(0, 255), + integers_in_range(0, 255), + integers_in_range(0, 255)) + def test_negate_non_zero(self, a, b, c, d): + ibm = IBMFloat.from_bytes((a, b, c, d)) + assume(not ibm.is_zero()) + negated = -ibm + self.assertNotEqual(ibm.signbit, negated.signbit) + + def test_negate_zero(self): + zero = IBMFloat.from_float(0.0) + negated = -zero + self.assertTrue(negated.is_zero()) + + @given(floats_in_range(MIN_IBM_FLOAT, MAX_IBM_FLOAT)) + def test_signbit(self, f): + ltz = f < 0 + ibm = IBMFloat.from_float(f) + self.assertEqual(ltz, ibm.signbit) + + @given(floats_in_range(-1.0, +1.0), + integers_in_range(-256, 255)) + def test_ldexp_frexp(self, fraction, exponent): + try: + ibm = IBMFloat.ldexp(fraction, exponent) + except OverflowError: + assume(False) + else: + f, e = ibm.frexp() + self.assertTrue(almost_equal(fraction * 2**exponent, f * 2**e, epsilon=EPSILON_IBM_FLOAT)) + + @given(floats_in_range(MIN_IBM_FLOAT, MAX_IBM_FLOAT), + floats_in_range(0.0, 1.0)) + def test_add(self, f, p): + a = f * p + b = f - a + + ibm_a = IBMFloat.from_float(a) + ibm_b = IBMFloat.from_float(b) + ibm_c = ibm_a + ibm_b + + ieee_a = float(ibm_a) + ieee_b = float(ibm_b) + ieee_c = ieee_a + ieee_b + + self.assertTrue(almost_equal(ieee_c, ibm_c, epsilon=EPSILON_IBM_FLOAT * 4)) + + @given(floats_in_range(0, MAX_IBM_FLOAT), + floats_in_range(0, MAX_IBM_FLOAT)) + def test_sub(self, a, b): + ibm_a = IBMFloat.from_float(a) + ibm_b = IBMFloat.from_float(b) + ibm_c = ibm_a - ibm_b + + ieee_a = float(ibm_a) + ieee_b = float(ibm_b) + ieee_c = ieee_a - ieee_b + + self.assertTrue(almost_equal(ieee_c, ibm_c, epsilon=EPSILON_IBM_FLOAT)) + + + +if __name__ == '__main__': + unittest.main() diff --git a/test/test_util.py b/test/test_util.py new file mode 100644 index 0000000..1b71b94 --- /dev/null +++ b/test/test_util.py @@ -0,0 +1,50 @@ +import unittest + +from hypothesis import given, assume +from hypothesis.descriptors import integers_in_range +from segpy.util import batched + + +class TestBatched(unittest.TestCase): + + @given([int], + integers_in_range(1, 1000)) + def test_batch_sizes_unpadded(self, items, batch_size): + assume(batch_size > 0) + batches = list(batched(items, batch_size)) + self.assertTrue(all(len(batch) == batch_size for batch in batches[:-1])) + + @given([int], + integers_in_range(1, 1000)) + def test_final_batch_sizes(self, items, batch_size): + assume(len(items) > 0) + assume(batch_size > 0) + batches = list(batched(items, batch_size)) + self.assertTrue(len(batches[-1]) <= batch_size) + + @given([int], + integers_in_range(1, 1000), + int) + def test_batch_sizes_padded(self, items, batch_size, pad): + assume(batch_size > 0) + batches = list(batched(items, batch_size, padding=pad)) + self.assertTrue(all(len(batch) == batch_size for batch in batches)) + + @given([int], + integers_in_range(1, 1000), + int) + def test_pad_contents(self, items, batch_size, pad): + assume(len(items) > 0) + assume(0 < batch_size < 1000) + num_left_over = len(items) % batch_size + pad_length = batch_size - num_left_over if num_left_over != 0 else 0 + assume(pad_length != 0) + batches = list(batched(items, batch_size, padding=pad)) + self.assertEqual(batches[-1][batch_size - pad_length:], [pad] * pad_length) + + def test_pad(self): + batches = list(batched([0, 0], 3, 42)) + self.assertEqual(batches[-1], [0, 0, 42]) + +if __name__ == '__main__': + unittest.main() \ No newline at end of file diff --git a/testsegy.py b/testsegy.py deleted file mode 100644 index 936cbfc..0000000 --- a/testsegy.py +++ /dev/null @@ -1,80 +0,0 @@ -#!/usr/bin/env python -# -# testsegy.py -# - -import segypy - - -def test_read(filename): - # Read Segy File - with open(filename, 'rb') as f: - return segypy.read_segy(f, filename) - - -def test_write(filename_out, data, sh, sth): - sh['DataSampleFormat'] = 5 - sh['SegyFormatRevisionNumber'] = 100 - segypy.write_segy_structure(filename_out, data, sh, sth) - - segypy.wiggle(data, sh, 2, .1, .1) - - f_ieee = 'data_IEEE.segy' - f_ibm = 'data_IBM_REV1.segy' - d_ieee, sh, sth = segypy.read_segy(f_ieee) - d_ibm, sh, sth = segypy.read_segy(f_ibm) - - return d_ieee, d_ibm, data - - -def test_render(d_ieee, d_ibm, data): - import pylab - - # imshow(Data) - pylab.figure(1) - pylab.imshow(d_ieee) - pylab.title('ieee') - pylab.show() - - pylab.figure(2) - pylab.imshow(d_ibm) - pylab.title('IBM') - pylab.show() - - pylab.figure(3) - pylab.imshow(data) - pylab.title('TEST') - pylab.show() - - -def parse_args(): - import argparse - - parser = argparse.ArgumentParser() - - parser.add_argument('filename', - help='The SEGY input file') - - parser.add_argument('--output', '-o', - dest='outfile', - default='', - help='The output file (optional).') - - parser.add_argument('--render_test', '-r', - dest='render_test', - action='store_true', - help='Whether to test rendering (only applies if ' - 'output is produced.)') - - return parser.parse_args() - -if __name__ == '__main__': - args = parse_args() - - read_results = test_read(args.filename) - - if args.outfile: - write_results = test_write(args.outfile, *read_results) - - if args.render_test: - test_render(*write_results)