Merge pull request #304 from PyThaiNLP/remove_tnc_word_freq

Remove pythainlp.corpus.tnc.word_freq

Author: bact

docs/api/corpus.rst

@@ -22,7 +22,6 @@ Modules
 TNC
 ---
 
-.. autofunction:: pythainlp.corpus.tnc.word_freq
 .. autofunction:: pythainlp.corpus.tnc.word_freqs
 
 TTC
@@ -51,4 +50,4 @@ Definition
 ++++++++++
 
 Synset
-    a set of synonyms that share a common meaning.
+    a set of synonyms that share a common meaning.

pythainlp/corpus/tnc.py

@@ -5,64 +5,14 @@
 Credit: Korakot Chaovavanich‎
 https://www.facebook.com/photo.php?fbid=363640477387469&set=gm.434330506948445&type=3&permPage=1
 """
-import re
 from typing import List, Tuple
 
-import requests
 from pythainlp.corpus import get_corpus
 
-__all__ = ["word_freq", "word_freqs"]
+__all__ = ["word_freqs"]
 
 _FILENAME = "tnc_freq.txt"
 
-
-def word_freq(word: str, domain: str = "all") -> int:
-    """
-
-    .. note::
-        **Not officially supported.**
-        Get word frequency of a word by domain.
-        This function will make a query to the server of
-        Thai National Corpus.
-        Internet connection is required.
-
-    .. warning::
-        Currently (as of 29 April 2019) it is likely to return 0,
-        regardless of the word, as the service URL has been changed
-        and the code is not updated yet.
-        New URL is http://www.arts.chula.ac.th/~ling/tnc3/
-
-    :param string word: word
-    :param string domain: domain
-    """
-    listdomain = {
-        "all": "",
-        "imaginative": "1",
-        "natural-pure-science": "2",
-        "applied-science": "3",
-        "social-science": "4",
-        "world-affairs-history": "5",
-        "commerce-finance": "6",
-        "arts": "7",
-        "belief-thought": "8",
-        "leisure": "9",
-        "others": "0",
-    }
-    url = "http://www.arts.chula.ac.th/~ling/tnc3/"
-    data = {"genre[]": "", "domain[]": listdomain[domain], "sortby": "perc", "p": word}
-
-    r = requests.post(url, data=data)
-
-    pat = re.compile(r'TOTAL</font>.*?#ffffff">(.*?)</font>', flags=re.DOTALL)
-    match = pat.search(r.text)
-
-    n = 0
-    if match:
-        n = int(match.group(1).strip())
-
-    return n
-
-
 def word_freqs() -> List[Tuple[str, int]]:
     """
     Get word frequency from Thai National Corpus (TNC)

tests/test_corpus.py

@@ -42,7 +42,6 @@ def test_corpus(self):
 
     def test_tnc(self):
         self.assertIsNotNone(tnc.word_freqs())
-        self.assertIsNotNone(tnc.word_freq("นก"))
 
     def test_ttc(self):
         self.assertIsNotNone(ttc.word_freqs())