From 89e8436cd0d2e145d1abd70f68c5b99a663d4b47 Mon Sep 17 00:00:00 2001
From: jvdhorst <you@example.com>
Date: Tue, 6 Mar 2018 14:09:26 +0100
Subject: [PATCH] Rewrote script to make use of functions.

---
 .DS_Store         | Bin 0 -> 6148 bytes
 src/wordtagger.py | 127 +++++++++++++++++++++++++---------------------
 2 files changed, 69 insertions(+), 58 deletions(-)
 create mode 100644 .DS_Store

diff --git a/.DS_Store b/.DS_Store
new file mode 100644
index 0000000000000000000000000000000000000000..7855ac459e100acc02c8d7fa4e3a813684848e9f
GIT binary patch
literal 6148
zcmeHK%}T>S5T3QQCW_dDpm^Ggw;ob|svd+;>%p54(Su4&Y-s~EktVfht>iuQjeG!K
z$C=$xtW{4UqB}7A&Hl_T^TF=y0D!3W8fAbY09dGm`DtuE5Sk|)lL;QlBMP-g6Oy2x
zTn3#u7+Y-y3<HLN-^Kvl-2#Mg0Y0=~^!`2umz^+49p_0*<noh+Da*Dkd)7Yn+Hv1Y
z{j`@<{q8aK_WiUSuze86omblr4#Q@@UYy^Fqtp+hW>-0fjV3NRISQjj+^@#HsFA3B
zJUyWfsu!0AgZ0WrNtV~Ph9x;DZ#oWkoDF9<w5^5Z^7h`@#r4hLc6fKMc@_8!DVbw@
zfd@23!o2djQ74XCI8Ht}NT3VnZyvAT5PW5`Qj#mq>Nf<>0lo|Sg&u?dkpaFe*35ql
z-o$JeFbsUj0KE?qmC$9(G^(cq8&v`z(l<g0+Eh!Bk7RTiGmSWdBD5=_b`@M=2<?vJ
zlGnM6nMUmnf{PEqCkw7nggPDfmufi(SEFeS1BQW726DPvr2N18dHp}?WO{}H!@!?n
zK;&y)t%@OWZXFAba;-!?LnWbgnMUP;4X0yeP%2(TRf2Pp3`CbP(}*J|<|CkJFpXj0
HM;UkqDua}Z

literal 0
HcmV?d00001

diff --git a/src/wordtagger.py b/src/wordtagger.py
index e0ccec4..fedc080 100644
--- a/src/wordtagger.py
+++ b/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
-words = nltk.word_tokenize(string)
-taggedwordlist = nltk.pos_tag(words)
-
-for word, pos in nltk.pos_tag(words):
+# FILTER FUNCTIONS
+# This function cuts a string into words. Then runs a POS tagger for each word. Returns a list with tags
+def postagger(string):
+    words = nltk.word_tokenize(string)
     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()