Commits

yanchuan sim  committed 34710a4

added MONEY

  • Participants
  • Parent commits 8af70d2

Comments (0)

Files changed (1)

File ycutils/tokenize.py

 import os, string, collections, unicodedata, itertools
 import regex as re # required
 
-__MONTHS__ = set(map(unicode, ['feb', 'oct', 'mar', 'aug', 'sep', 'jan', 'jun', 'apr', 'dec', 'jul', 'nov', 'january', 'february', 'march', 'april', 'may', 'june', 'july', 'august', 'september', 'october', 'november', 'december']))
+MONTHS = set(map(unicode, ['feb', 'oct', 'mar', 'aug', 'sep', 'jan', 'jun', 'apr', 'dec', 'jul', 'nov', 'january', 'february', 'march', 'april', 'may', 'june', 'july', 'august', 'september', 'october', 'november', 'december']))
+"""Month names that will be tagged as :attr:`TAG_MONTH`."""
 
 STOPWORDS = set(map(unicode, ['a', 'a\'s', 'able', 'about', 'above', 'according', 'accordingly', 'across', 'actually', 'after', 'afterwards', 'again', 'against', 'ain\'t', 'all', 'allow', 'allows', 'almost', 'alone', 'along', 'already', 'also', 'although', 'always', 'am', 'among', 'amongst', 'an', 'and', 'another', 'any', 'anybody', 'anyhow', 'anyone', 'anything', 'anyway', 'anyways', 'anywhere', 'apart', 'appear', 'appreciate', 'appropriate', 'are', 'aren\'t', 'around', 'as', 'aside', 'ask', 'asking', 'associated', 'at', 'available', 'away', 'awfully', 'be', 'became', 'because', 'become', 'becomes', 'becoming', 'been', 'before', 'beforehand', 'behind', 'being', 'believe', 'below', 'beside', 'besides', 'best', 'better', 'between', 'beyond', 'both', 'brief', 'but', 'by', 'c\'mon', 'c\'s', 'came', 'can', 'can\'t', 'cannot', 'cant', 'cause', 'causes', 'certain', 'certainly', 'changes', 'clearly', 'co', 'com', 'come', 'comes', 'concerning', 'consequently', 'consider', 'considering', 'contain', 'containing', 'contains', 'corresponding', 'could', 'couldn\'t', 'course', 'currently', 'definitely', 'described', 'despite', 'did', 'didn\'t', 'different', 'do', 'does', 'doesn\'t', 'doing', 'don\'t', 'done', 'down', 'downwards', 'during', 'each', 'edu', 'eg', 'eight', 'either', 'else', 'elsewhere', 'enough', 'entirely', 'especially', 'et', 'etc', 'even', 'ever', 'every', 'everybody', 'everyone', 'everything', 'everywhere', 'ex', 'exactly', 'example', 'except', 'far', 'few', 'fifth', 'first', 'five', 'followed', 'following', 'follows', 'for', 'former', 'formerly', 'forth', 'four', 'from', 'further', 'furthermore', 'get', 'gets', 'getting', 'given', 'gives', 'go', 'goes', 'going', 'gone', 'got', 'gotten', 'greetings', 'had', 'hadn\'t', 'happens', 'hardly', 'has', 'hasn\'t', 'have', 'haven\'t', 'having', 'he', 'he\'s', 'hello', 'help', 'hence', 'her', 'here', 'here\'s', 'hereafter', 'hereby', 'herein', 'hereupon', 'hers', 'herself', 'hi', 'him', 'himself', 'his', 'hither', 'hopefully', 'how', 'howbeit', 'however', 'i\'d', 'i\'ll', 'i\'m', 'i\'ve', 'ie', 'if', 'ignored', 'immediate', 'in', 'inasmuch', 'inc', 'indeed', 'indicate', 'indicated', 'indicates', 'inner', 'insofar', 'instead', 'into', 'inward', 'is', 'isn\'t', 'it', 'it\'d', 'it\'ll', 'it\'s', 'its', 'itself', 'just', 'keep', 'keeps', 'kept', 'know', 'known', 'knows', 'last', 'lately', 'later', 'latter', 'latterly', 'least', 'less', 'lest', 'let', 'let\'s', 'like', 'liked', 'likely', 'little', 'look', 'looking', 'looks', 'ltd', 'mainly', 'many', 'may', 'maybe', 'me', 'mean', 'meanwhile', 'merely', 'might', 'more', 'moreover', 'most', 'mostly', 'much', 'must', 'my', 'myself', 'name', 'namely', 'nd', 'near', 'nearly', 'necessary', 'need', 'needs', 'neither', 'never', 'nevertheless', 'new', 'next', 'nine', 'no', 'nobody', 'non', 'none', 'noone', 'nor', 'normally', 'not', 'nothing', 'novel', 'now', 'nowhere', 'obviously', 'of', 'off', 'often', 'oh', 'ok', 'okay', 'old', 'on', 'once', 'one', 'ones', 'only', 'onto', 'or', 'other', 'others', 'otherwise', 'ought', 'our', 'ours', 'ourselves', 'out', 'outside', 'over', 'overall', 'own', 'particular', 'particularly', 'per', 'perhaps', 'placed', 'please', 'plus', 'possible', 'presumably', 'probably', 'provides', 'que', 'quite', 'qv', 'rather', 'rd', 're', 'really', 'reasonably', 'regarding', 'regardless', 'regards', 'relatively', 'respectively', 'right', 'said', 'same', 'saw', 'say', 'saying', 'says', 'second', 'secondly', 'see', 'seeing', 'seem', 'seemed', 'seeming', 'seems', 'seen', 'self', 'selves', 'sensible', 'sent', 'serious', 'seriously', 'seven', 'several', 'shall', 'she', 'should', 'shouldn\'t', 'since', 'six', 'so', 'some', 'somebody', 'somehow', 'someone', 'something', 'sometime', 'sometimes', 'somewhat', 'somewhere', 'soon', 'sorry', 'specified', 'specify', 'specifying', 'still', 'sub', 'such', 'sup', 'sure', 't\'s', 'take', 'taken', 'tell', 'tends', 'th', 'than', 'thank', 'thanks', 'thanx', 'that', 'that\'s', 'thats', 'the', 'their', 'theirs', 'them', 'themselves', 'then', 'thence', 'there', 'there\'s', 'thereafter', 'thereby', 'therefore', 'therein', 'theres', 'thereupon', 'these', 'they', 'they\'d', 'they\'ll', 'they\'re', 'they\'ve', 'think', 'third', 'this', 'thorough', 'thoroughly', 'those', 'though', 'three', 'through', 'throughout', 'thru', 'thus', 'to', 'together', 'too', 'took', 'toward', 'towards', 'tried', 'tries', 'truly', 'try', 'trying', 'twice', 'two', 'un', 'under', 'unfortunately', 'unless', 'unlikely', 'until', 'unto', 'up', 'upon', 'us', 'use', 'used', 'useful', 'uses', 'using', 'usually', 'value', 'various', 'very', 'via', 'viz', 'vs', 'want', 'wants', 'was', 'wasn\'t', 'way', 'we', 'we\'d', 'we\'ll', 'we\'re', 'we\'ve', 'welcome', 'well', 'went', 'were', 'weren\'t', 'what', 'what\'s', 'whatever', 'when', 'whence', 'whenever', 'where', 'where\'s', 'whereafter', 'whereas', 'whereby', 'wherein', 'whereupon', 'wherever', 'whether', 'which', 'while', 'whither', 'who', 'who\'s', 'whoever', 'whole', 'whom', 'whose', 'why', 'will', 'willing', 'wish', 'with', 'within', 'without', 'won\'t', 'wonder', 'would', 'wouldn\'t', 'yes', 'yet', 'you', 'you\'d', 'you\'ll', 'you\'re', 'you\'ve', 'your', 'yours', 'yourself', 'yourselves', 'zero']))
 """Stopwords based on MySQL <http://dev.mysql.com/doc/refman/5.5/en/fulltext-stopwords.html>"""
 # __TRANS_UNICODE__ = dict([(ord(c), u' ') for c in u'!"#$%&()*+,./:;<=>?@[\\]^`{|}~'] + [(ord(u'-'), None)]) # \', _, - not in here
 # __TRANS_ASCII__ = string.maketrans('!"#$%&()*+,./:;<=>?@[\\]^`{|}~', ' ' * 29)
 
-__DEFAULT_NORMALIZE__ = ['case', 'consecutive', 'phone', 'time', 'url', 'email', 'number', 'money', 'punct-del', 'hyphen-split', 'clitics-del', 'neg-clitics-keep']
-__DEFAULT_TAG_LIST__ = ['phone', 'time', 'url', 'email', 'number', 'money']
+__DEFAULT_NORMALIZE__ = ['case', 'consecutive', 'phone', 'time', 'month', 'url', 'email', 'number', 'money', 'punct-del', 'hyphen-split', 'clitics-del', 'neg-clitics-keep']
+__DEFAULT_TAG_LIST__ = ['phone', 'time', 'month', 'url', 'email', 'number', 'money']
 
 TAG_EMPTY = 0
 """Tag returned by :meth:`tag_tokens` to mean empty tokens."""
 TAG_TIME = 11
 """Tag returned by :meth:`tag_tokens` to mean time tokens."""
 
+TAG_MONTH = 12
+"""Tag returned by :meth:`tag_tokens` to mean month tokens."""
+
 TAG_PHONE = 20
 """Tag returned by :meth:`tag_tokens` to mean phone number (US) tokens."""
 
   * ``email``: Replace email addresses with ``__EMAIL__``.
   * ``number``: Replace numbers with ``__NUM__``.
   * ``money``: Replace currency with ``__MONEY__``.
+  * ``month``: Replace month names with ``__MONTH__``.
   * ``punct-split``: Separate punctuations into their own tokens. However, consecutive punctuations will be considered as a single token.
   * ``punct-del``: Remove all punctuations except hyphens, dashes, single quotes and those specified in :attr:`not_punctuations`.
   * ``hyphen-split``: Separate hyphenated tokens into individual tokens. Hyphens are removed in the process.
 
     if tag == TAG_PHONE and 'phone' in normalize: tok = '__PHONE__'
     elif tag == TAG_TIME and 'time' in normalize: tok = '__TIME__'
+    elif tag == TAG_MONTH and 'month' in normalize: tok = '__MONTH__'
     elif tag == TAG_EMAIL and 'email' in normalize: tok = '__EMAIL__'
     elif tag == TAG_NUM and 'number' in normalize: tok = '__NUM__'
     elif tag == TAG_URL and 'url' in normalize: tok = '__URL__'
     for i, tok in enumerate(tokens):
       if __RE_TIME__.match(tok): tags[i] = TAG_TIME
 
+  if 'month' in tag_list:
+    for i, tok in enumerate(tokens):
+      if tok in MONTHS: tags[i] = TAG_MONTH
+
   if 'email' in tag_list:
     for i, tok in enumerate(tokens):
       if __RE_EMAIL__.match(tok): tags[i] = TAG_EMAIL