Merge branch 'master' of git.xpub.nl:/var/www/git.xpub.nl/repos/OuNoPo-make

Makefile

@@ -61,7 +61,7 @@ output/tagged-words.txt: ocr/output.txt ## Analyzes OCR'ed text using a Part of
 #  >>> import nltk
 #  >>> nltk.download('averaged_perceptron_tagger')
 
-output/chatbot.txt: ocr/output.txt ## DESCRIBE WHAT IT DOES. Dependencies: python3's chatterbot
+output/chatbot.txt: ocr/output.txt ## Comments a text with a simple chatbot. Dependencies: python3's chatterbot
 	cat $< | python3 src/textbotconversation.py $(@)
 
 

src/wordtagger.py

@@ -1,71 +1,82 @@
 import nltk
 from sys import stdin, stdout
 
-# Step 1: define input and set up a list
+# Define input
 input = stdin.read()
-taggedwordlist = []
 
-string = input
+# FILTER FUNCTIONS
-words = nltk.word_tokenize(string)
+# This function cuts a string into words. Then runs a POS tagger for each word. Returns a list with tags
-taggedwordlist = nltk.pos_tag(words)
+def postagger(string):
-
+    words = nltk.word_tokenize(string)
-for word, pos in nltk.pos_tag(words):
     taggedwordlist = nltk.pos_tag(words)
-    # print('{0} is a {1}'.format(word,pos)) # Command out to print the analysis step
 
+    for word, pos in nltk.pos_tag(words):
+        taggedwordlist = nltk.pos_tag(words)
+        #print('{0} is a {1}'.format(word,pos)) # Comment out to print the analysis step
+
+    taglist = [ pos for word,pos in taggedwordlist ]
+    #print(taglist)
+    return taglist;
 
-taglist = [ pos for word,pos in taggedwordlist ]
+# This function changes the tags to readable equivalents (NNP to noun for example)
+def postagger_readable(list):
+    readabletaglist = []
 
-#print(taglist)
+    for tag in list:
+        if tag in {"NNP","NNS","NN","NNPS"}:
+            readabletag = 'noun'
+        elif tag in {'VB','VBD','VBG','VBN','VBP','VBZ'}:
+            readabletag = 'verb'
+        elif tag in {'RB','RBR','RBS','WRB'}:
+            readabletag = 'adverb'
+        elif tag in {'PRP','PRP$'}:
+            readabletag = 'pronoun'
+        elif tag in {'JJ','JJR','JJS'}:
+            readabletag = 'adjective'
+        elif tag == 'IN':
+            readabletag = 'preposition'
+        elif tag == 'WDT':
+            readabletag = 'determiner'
+        elif tag in {'WP','WP$'}:
+            readabletag = 'pronoun'
+        elif tag == 'UH':
+            readabletag = 'interjection'
+        elif tag == 'POS':
+            readabletag = 'possesive ending'
+        elif tag == 'SYM':
+            readabletag = 'symbol'
+        elif tag == 'EX':
+            readabletag = 'existential there'
+        elif tag == 'DT':
+            readabletag = 'determiner'
+        elif tag == 'MD':
+            readabletag = 'modal'
+        elif tag == 'LS':
+            readabletag = 'list item marker'
+        elif tag == 'FW':
+            readabletag = 'foreign word'
+        elif tag == 'CC':
+            readabletag = 'coordinating conjunction '
+        elif tag == 'CD':
+            readabletag = 'cardinal number'
+        elif tag == 'TO':
+            readabletag = 'to'
+        elif tag == '.':
+            readabletag = 'line ending'
+        elif tag == ',':
+            readabletag = 'comma'
+        else:
+            readabletag = tag
 
-readabletaglist = []
+        readabletaglist.append(readabletag)
+    return readabletaglist;
 
-for tag in taglist:
-    if tag in {"NNP","NNS","NN","NNPS"}:
-        readabletag = 'noun'
-    elif tag in {'VB','VBD','VBG','VBN','VBP','VBZ'}:
-        readabletag = 'verb'
-    elif tag in {'RB','RBR','RBS','WRB'}:
-        readabletag = 'adverb'
-    elif tag in {'PRP','PRP$'}:
-        readabletag = 'pronoun'
-    elif tag in {'JJ','JJR','JJS'}:
-        readabletag = 'adjective'
-    elif tag == 'IN':
-        readabletag = 'preposition'
-    elif tag == 'WDT':
-        readabletag = 'determiner'
-    elif tag in {'WP','WP$'}:
-        readabletag = 'pronoun'
-    elif tag == 'UH':
-        readabletag = 'interjection'
-    elif tag == 'POS':
-        readabletag = 'possesive ending'
-    elif tag == 'SYM':
-        readabletag = 'symbol'
-    elif tag == 'EX':
-        readabletag = 'existential there'
-    elif tag == 'DT':
-        readabletag = 'determiner'
-    elif tag == 'MD':
-        readabletag = 'modal'
-    elif tag == 'LS':
-        readabletag = 'list item marker'
-    elif tag == 'FW':
-        readabletag = 'foreign word'
-    elif tag == 'CC':
-        readabletag = 'coordinating conjunction '
-    elif tag == 'CD':
-        readabletag = 'cardinal number'
-    elif tag == 'TO':
-        readabletag = 'to'
-    elif tag == '.':
-        readabletag = 'line ending'
-    elif tag == ',':
-        readabletag = 'comma'
-    else:
-        readabletag = tag
 
-    readabletaglist.append(readabletag)
+# This function creates the output
+def main():
+    taglist = postagger(input)
+    readabletaglist = postagger_readable(taglist)
+    stdout.write(' '.join(readabletaglist))
+    stdout.write('\n')
 
-stdout.write(' '.join(readabletaglist))
+main()