class Preprocessor(object):
def __init__(self, source_filename, target_filename, include_filenames):
self.reader = Reader(source_filename)
for filename in include_filenames:
self.reader.include(filename)
self.writer = Writer(target_filename)
self.defines = {}
self.lines = self.reader.get_lines() # это генератор
def define(self, line):
pass
def include(self, line):
pass
def process(self, line):
return True
def run(self):
for line in self.lines:
if self.process(line):
self.writer.write_line(line)
def close(self):
self.reader.close()
self.writer.close()
def __init__(self, source_filename, target_filename, include_filenames):
self.reader = Reader(source_filename)
for filename in include_filenames:
self.reader.include(filename)
self.writer = Writer(target_filename)
self.defines = {}
self.lines = self.reader.get_lines() # это генератор
def indexing(self,
files,
ignore_case=True,
ignore_stop_words=True,
stemming=True,
use_weights=True,
title_weight=5,
date_weight=2,
memory_limit=50,
use_vbytes=True):
"""
Launch the indexing of a list of files
:param files: the paths to the files to index
:param ignore_case: should case be ignored in the indexing ?
:param ignore_stop_words: should stop words be ignored ?
:param stemming: should we stemm the tokens ?
:param use_weights: shoud we differenciate word with their position in the document ?
:param title_weight: weight for words in title
:param date_weight: weight for words in the date
:param memory_limit: limit on the memory before a flush in a temp file
:param use_vbytes: usage of variable bytes for the final posting list ?
:return: when the indexing is finished
"""
SC.new_indexing()
documents = []
self.current_status = "Indexing - Starting"
self.__id_to_filename = SortedDict()
self.inv_file = InvertedFile(use_vbytes, memory_limit)
for file in files:
self.current_status = "Indexing - {}".format(file)
file_docs = Reader.read_file(file, ignore_case, ignore_stop_words,
stemming, use_weights, title_weight,
date_weight)
for doc in file_docs:
self.__id_to_filename[int(doc.doc_id())] = file
self.inv_file.add_document(doc)
self.current_status = "Indexing - Making the inverted file"
self.inv_file.gen_pl_file()
self.current_status = "Indexing - Saving to pickle file"
with open(self.PICKLES[0], "wb") as file:
pickle.dump(self.inv_file, file)
with open(self.PICKLES[1], "wb") as file:
pickle.dump(self.__id_to_filename, file)
self.current_status = "Indexing - Finished - You can query"
SC.last_indexing().stop()
SC.last_indexing().log(files, ignore_case, ignore_stop_words, stemming,
use_weights, title_weight, date_weight,
memory_limit, use_vbytes)
