Created
January 28, 2012 17:20
-
-
Save elidickinson/1695094 to your computer and use it in GitHub Desktop.
show how to access libots C library from Python
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| from ctypes import * | |
| from ctypeslib.contrib.pythonhdr import * | |
| def quick_summary(data,words=150): | |
| ots = OTS() | |
| ots.parse_string(data) | |
| return ots.summarize_by_words(words) | |
| class OTS: | |
| libots = None | |
| article = None | |
| dict_name = "en" | |
| def __init__(self): | |
| cdll.LoadLibrary('libots-1.so.0.5.0') | |
| self.libots = CDLL('libots-1.so.0.5.0') | |
| def parse_file(self,fname): | |
| self.article = self.libots.ots_new_article() | |
| self.libots.ots_load_xml_dictionary(self.article,self.dict_name) | |
| f = open(fname,'r') | |
| self.libots.ots_parse_file(PyFile_AsFile(f),self.article) #0 | |
| f.close() | |
| self.libots.ots_grade_doc(self.article) | |
| def parse_string(self,data): | |
| self.article = self.libots.ots_new_article() | |
| self.libots.ots_load_xml_dictionary(self.article,self.dict_name) | |
| if type(data) == unicode: | |
| data = unicode.encode(data, 'utf-8') | |
| self.libots.ots_parse_stream(data, len(data), self.article) | |
| self.libots.ots_grade_doc(self.article) | |
| def article_word_count(self): | |
| return self.libots.ots_get_article_word_count(self.article) | |
| def summarize_by_words(self,word_count=150): | |
| self.libots.ots_highlight_doc_words(self.article,word_count) | |
| summary = self._get_summary_string() | |
| summary = summary.decode('utf-8') | |
| return summary | |
| def _get_summary_string(self): | |
| # get summary as string | |
| bytes_out = c_int() | |
| self.libots.ots_get_doc_text.restype = c_char_p | |
| summary = self.libots.ots_get_doc_text(self.article,byref(bytes_out)) | |
| return summary |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| from ctypes import * | |
| from ctypeslib.contrib.pythonhdr import * | |
| cdll.LoadLibrary('libots-1.so.0.5.0') | |
| libots = CDLL('libots-1.so.0.5.0') | |
| f = open('/home/eli/article1.txt','r') | |
| art = libots.ots_new_article() | |
| # load dict | |
| libots.ots_load_xml_dictionary(art,"en") | |
| libots.ots_parse_file(PyFile_AsFile(f),art) #0 | |
| word_count = libots.ots_get_article_word_count(art) | |
| print "%d words in the article" % word_count | |
| libots.ots_grade_doc(art) | |
| # libots.ots_highlight_doc (art, 2) | |
| libots.ots_highlight_doc_words(art,200) | |
| bytes_out = c_int() | |
| libots.ots_get_doc_text.restype = c_char_p | |
| summary = libots.ots_get_doc_text(art,byref(bytes_out)) | |
| print summary | |
| libots.ots_free_article(art); | |
| f.close() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
More info here: http://www.elidickinson.com/story/using-libots-summary-library-with-python/2012-01