DOCUMENTATION: Formatting fix

Based on regular expressions with some keyword parameters
to simplify search queries.  A set of examples is
provided.

README.rst

@@ -39,10 +39,20 @@ What can you do with this library?
   
     pysle.syllabifyTextgrid(isleDict, praatioTextgrid, "words", "phones")
 
+- search for words based on pronunciation::
 
+    e.g. Words that start with a sound, or have a sound word medially, or 
+    in stressed vowel position, etc.
+    
+    see /tests/dictionary_search.py
+    
 Major revisions
 ================
 
+Ver 1.4 (July 9, 2016)
+
+- added search functionality
+
 Ver 1.3 (March 15, 2016)
 
 - added indicies for stressed vowels
@@ -139,7 +149,7 @@ Acknowledgements
 
 Development of Pysle was possible thanks to NSF grant **IIS 07-03624**
 to Jennifer Cole and Mark Hasegawa-Johnson, NSF grant **BCS 12-51343**
-to Jennifer Cole, José Hualde, and Caroline Smith, and
-to the A*MIDEX project (n° **ANR-11-IDEX-0001-02**) to James Sneed German
-funded by the Investissements d’Avenir French Government program, managed
+to Jennifer Cole, José Hualde, and Caroline Smith, and
+to the A*MIDEX project (n° **ANR-11-IDEX-0001-02**) to James Sneed German
+funded by the Investissements d'Avenir French Government program, managed
 by the French National Research Agency (ANR).

pysle/isletool.py

@@ -4,10 +4,27 @@ Created on Oct 11, 2012
 @author: timmahrt
 '''
 
+import io
+import re
+
+charList = ['#', '&', '&r', '3r', '9r', '>', '>i', '@', 'A', 'D', 'E',
+            'I', 'N', 'S', 'T', 'U', 'Z', '^', 'a', 'aI', 'aU', 'b',
+            'd', 'dZ', 'd_(', 'e', 'ei', 'f', 'g', 'h', 'i', 'i:',
+            'j', 'k', 'kh', 'l', 'l=', 'm', 'n', 'n=', 'oU', 'p',
+            'ph', 'r', 's', 'sh', 't', 'tS', 't_(', 'th', 'u',
+            'v', 'w', 'y', 'z']
 
 vowelList = ['a', '@', 'e', 'i', 'o', 'u', '^', '&', '>', ]
 
 
+def isVowel(char):
+    return any([vowel in char for vowel in vowelList])
+
+
+def sequenceMatch(matchChar, searchStr):
+    return matchChar in searchStr
+
+
 class WordNotInISLE(Exception):
     
     def __init__(self, word):
@@ -30,7 +47,8 @@ class LexicalTool():
         Builds the isle textfile into a dictionary for fast searching
         '''
         lexDict = {}
-        wordList = [line.rstrip('\n') for line in open(self.islePath, "rU")]
+        with io.open(self.islePath, "r", encoding='utf-8') as fd:
+            wordList = [line.rstrip('\n') for line in fd]
             
         for row in wordList:
             word, pronunciation = row.split(" ", 1)
@@ -60,6 +78,123 @@ class LexicalTool():
         
         return pronList
 
+    def search(self, matchStr, numSyllables=None, wordInitial='ok',
+               wordFinal='ok', spanSyllable='ok', stressedSyllable='ok',
+               multiword='ok'):
+        return search(self.data.items(), matchStr, numSyllables=numSyllables,
+                      wordInitial=wordInitial, wordFinal=wordFinal,
+                      spanSyllable=spanSyllable,
+                      stressedSyllable=stressedSyllable,
+                      multiword=multiword)
+
+
+def search(searchList, matchStr, numSyllables=None, wordInitial='ok',
+           wordFinal='ok', spanSyllable='ok', stressedSyllable='ok',
+           multiword='ok'):
+    '''
+    Searches for matching words in the dictionary with regular expressions
+    
+    wordInitial, wordFinal, spanSyllable, stressSyllable, and multiword
+    can take three different values: 'ok', 'only', or 'no'.
+    
+    Special search characters:
+    'V' - any vowel
+    'R' - any rhotic
+    '#' - word boundary
+    'B' - syllable boundary
+    '.' - anything
+    
+    Regular expression syntax applies, so if you wanted to search for any
+    word ending with a vowel or rhotic, matchStr = '(?:VR)#'
+    '''
+    
+    # Characters to check between all other characters
+    # Don't check between all other characters if the character is already
+    # in the search string or
+    interleaveStr = None
+    stressOpt = (stressedSyllable == 'ok' or stressedSyllable == 'only')
+    spanOpt = (spanSyllable == 'ok' or spanSyllable == 'only')
+    if stressOpt and spanOpt:
+        interleaveStr = "\.?'?"
+    elif stressOpt:
+        interleaveStr = "'?"
+    elif spanOpt:
+        interleaveStr = "\.?"
+    
+    if interleaveStr is not None:
+        matchStr = interleaveStr.join(matchStr)
+    
+    # Setting search boundaries
+    # We search on '[^\.#]' and not '.' so that the search doesn't span
+    # multiple syllables or words
+    if wordInitial == 'only':
+        matchStr = '#' + matchStr
+    elif wordInitial == 'no':
+        # Match the closest preceeding syllable.  If there is none, look
+        # for word boundary plus at least one other character
+        matchStr = '(?:\.[^\.#]*?|#[^\.#]+?)' + matchStr
+    else:
+        matchStr = '[#\.][^\.#]*?' + matchStr
+    
+    if wordFinal == 'only':
+        matchStr = matchStr + '#'
+    elif wordFinal == 'no':
+        matchStr = matchStr + "(?:[^\.#]*?\.|[^\.#]+?#)"
+    else:
+        matchStr = matchStr + '[^\.#]*?[#\.]'
+    
+    # Replace special characters
+    replDict = {"V": "(?:aI|aU|ei|oU|[AEIaeiu]):?",
+                "R": "[&39]?r",
+                "B": "\."}
+    
+    for char, replStr in replDict.items():
+        matchStr = matchStr.replace(char, replStr)
+    
+    # Run search for words
+    compiledRE = re.compile(matchStr)
+    retList = []
+    for word, pronList in searchList:
+        newPronList = []
+        for pron in pronList:
+            searchPron = pron.replace(",", "").replace(" ", "")
+            if numSyllables is not None:
+                if numSyllables != searchPron.count('.') + 1:
+                    continue
+            
+            # Is this a compound word?
+            if multiword == 'only':
+                if searchPron.count('#') == 2:
+                    continue
+            elif multiword == 'no':
+                if searchPron.count('#') > 2:
+                    continue
+            
+            matchList = compiledRE.findall(searchPron)
+            if len(matchList) > 0:
+                if stressedSyllable == 'only':
+                    if all(["'" not in match for match in matchList]):
+                        continue
+                if stressedSyllable == 'no':
+                    if all(["'" in match for match in matchList]):
+                        continue
+                
+                # For syllable spanning, we check if there is a syllable
+                # marker inside (not at the border) of the match.
+                if spanSyllable == 'only':
+                    if all(["." not in txt[1:-1] for txt in matchList]):
+                        continue
+                if spanSyllable == 'no':
+                    if all(["." in txt[1:-1] for txt in matchList]):
+                        continue
+                newPronList.append(pron)
+        
+        if len(newPronList) > 0:
+            retList.append((word, newPronList))
+    
+    retList.sort()
+    return retList
+
 
 def _parsePronunciation(pronunciationStr):
     '''

setup.py

@@ -1,16 +1,19 @@
+#!/usr/bin/env python
+# encoding: utf-8
 '''
 Created on Oct 15, 2014
 
 @author: tmahrt
 '''
+import codecs
 from distutils.core import setup
 setup(name='pysle',
-      version='1.3.0',
+      version='1.4.0',
       author='Tim Mahrt',
       author_email='timmahrt@gmail.com',
       package_dir={'pysle':'pysle'},
       packages=['pysle'],
       license='LICENSE',
-      long_description=open('README.rst', 'r').read(),
+      long_description=codecs.open('README.rst', 'r', encoding="utf-8").read(),
 #       install_requires=[], # No requirements! # requires 'from setuptools import setup'
       )

test/basic_examples.py

@@ -35,10 +35,12 @@ returnList = pronunciationtools.findBestSyllabification(isleDict,
                                                         searchWord, 
                                                         anotherPhoneList)
 
-stressedSyllable, syllableList, syllabification, stressedIndex = returnList
-
+(stressedSyllable, syllableList, syllabification,
+stressedSyllableIndexList, stressedPhoneIndexList,
+flattenedStressIndexList) = returnList
 print(searchWord)
 print(anotherPhoneList)
-print(syllableList) # We can see the first syllable was elided
-
+print(stressedSyllableIndexList) # We can see the first syllable was elided
+print(stressedPhoneIndexList)
+print(flattenedStressIndexList)
 

test/dictionary_search.py

@@ -0,0 +1,54 @@
+'''
+Created on July 08, 2016
+
+@author: tmahrt
+
+Basic examples of common usage.
+'''
+
+import random
+
+from pysle import isletool
+
+tmpPath = r"C:\Users\Tim\Dropbox\workspace\pysle\test\islev2.txt"
+isleDict = isletool.LexicalTool(tmpPath)
+
+def printOutMatches(matchStr, numSyllables=None, wordInitial='ok',
+                    wordFinal='ok', spanSyllable='ok', stressedSyllable='ok',
+                    multiword='ok', numMatches=None, matchList=None):
+
+    if matchList is None:
+        matchList = isleDict.search(matchStr, numSyllables, wordInitial,
+                                    wordFinal, spanSyllable, stressedSyllable,
+                                    multiword)
+    else:
+        matchList = isletool.search(matchList, matchStr, numSyllables, wordInitial,
+                                    wordFinal, spanSyllable, stressedSyllable,
+                                    multiword)
+    
+    if numMatches is not None and len(matchList) > numMatches:
+        random.shuffle(matchList)
+        
+    for i, matchTuple in enumerate(matchList):
+        if numMatches is not None and i > numMatches:
+            break
+        word, pronList = matchTuple
+        print("%s: %s" % (word, repr(pronList)))
+    print("")
+    
+    return matchList
+
+# 2-syllable words with a stressed syllable containing 'dV' but not word initially
+printOutMatches("dV", stressedSyllable="only", spanSyllable="no",
+                wordInitial="no", numSyllables=2, numMatches=10)
+ 
+# 3-syllable word with an 'ld' sequence that spans a syllable boundary
+printOutMatches("lBd", wordInitial="no", multiword='no',
+                numSyllables=3, numMatches=10)
+
+# words ending in 'inth'
+matchList = printOutMatches("InT", wordFinal="only", numMatches=10)
+
+# that also start with 's'
+matchList = printOutMatches("s", wordInitial="only", numMatches=10,
+                            matchList=matchList, multiword="no")