home | career | drupal | java | mac | mysql | perl | scala | uml | unix  

Lucene example source code file (makeEuroparlLineFile.py)

This example Lucene source code file (makeEuroparlLineFile.py) is included in the DevDaily.com "Java Source Code Warehouse" project. The intent of this project is to help you "Learn Java by Example" TM.

Java - Lucene tags/keywords

apache, europarl, false, false, license, license, none, none, true, v5, valueerror, verbose, verbose, you

The Lucene makeEuroparlLineFile.py source code

# Licensed to the Apache Software Foundation (ASF) under one or more
# contributor license agreements.  See the NOTICE file distributed with
# this work for additional information regarding copyright ownership.
# The ASF licenses this file to You under the Apache License, Version 2.0
# (the "License"); you may not use this file except in compliance with
# the License.  You may obtain a copy of the License at
#     http://www.apache.org/licenses/LICENSE-2.0
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# See the License for the specific language governing permissions and
# limitations under the License.

import sys
import glob
import datetime
import tarfile
import re

  VERBOSE = True
except ValueError:
  VERBOSE = False

  docPerParagraph = True
except ValueError:
  docPerParagraph = False

reChapterOnly = re.compile('^<CHAPTER ID=.*?>$')
reTagOnly = re.compile('^<.*?>$')
reNumberOnly = re.compile(r'^\d+\.?$')

docCount = 0
didEnglish = False

def write(date, title, pending, fOut):
  global docCount
  body = ' '.join(pending).replace('\t', ' ').strip()
  if len(body) > 0:
    line = '%s\t%s\t%s\n' % (title, date, body)
    docCount += 1
    del pending[:]
    if VERBOSE:
      print len(body)

def processTar(fileName, fOut):

  global didEnglish

  t = tarfile.open(fileName, 'r:gz')
  for ti in t:
    if ti.isfile() and (not didEnglish or ti.name.find('/en/') == -1):

      tup = ti.name.split('/')
      lang = tup[1]
      year = int(tup[2][3:5])
      if year < 20:
        year += 2000
        year += 1900

      month = int(tup[2][6:8])
      day = int(tup[2][9:11])
      date = datetime.date(year=year, month=month, day=day)

      if VERBOSE:
        print '%s: %s' % (ti.name, date)
      nextIsTitle = False
      title = None
      pending = []
      for line in t.extractfile(ti).readlines():
        line = line.strip()
        if reChapterOnly.match(line) is not None:
          if title is not None:
            write(date, title, pending, fOut)
          nextIsTitle = True
        if nextIsTitle:
          if not reNumberOnly.match(line) and not reTagOnly.match(line):
            title = line
            nextIsTitle = False
            if VERBOSE:
              print '  title %s' % line
        if line.lower() == '<p>':
          if docPerParagraph:
            write(date, title, pending, fOut)
        elif not reTagOnly.match(line):
      if title is not None and len(pending) > 0:
        write(date, title, pending, fOut)

  didEnglish = True
# '/x/lucene/data/europarl/all.lines.txt'
dirIn = sys.argv[1]
fileOut = sys.argv[2]
fOut = open(fileOut, 'wb')

for fileName in glob.glob('%s/??-??.tgz' % dirIn):
  if fileName.endswith('.tgz'):
    print 'process %s; %d docs so far...' % (fileName, docCount)
    processTar(fileName, fOut)

print 'TOTAL: %s' % docCount

#run something like this:

# Europarl V5 makes 76,917 docs, avg 38.6 KB per
python -u europarl.py /x/lucene/data/europarl /x/lucene/data/europarl/tmp.lines.txt
shuf /x/lucene/data/europarl/tmp.lines.txt > /x/lucene/data/europarl/full.lines.txt
rm /x/lucene/data/europarl/tmp.lines.txt

# Run again, this time each paragraph is a doc:
# Europarl V5 makes 5,607,746 paragraphs (one paragraph per line), avg 620 bytes per:
python -u europarl.py /x/lucene/data/europarl /x/lucene/data/europarl/tmp.lines.txt -docPerParagraph
shuf /x/lucene/data/europarl/tmp.lines.txt > /x/lucene/data/europarl/para.lines.txt
rm /x/lucene/data/europarl/tmp.lines.txt

# ~5.5 MB gzip'd:
head -200 /x/lucene/data/europarl/full.lines.txt > tmp.txt
head -10000 /x/lucene/data/europarl/para.lines.txt >> tmp.txt
shuf tmp.txt > europarl.subset.txt
rm -f tmp.txt
gzip --best europarl.subset.txt

Other Lucene examples (source code examples)

Here is a short list of links related to this Lucene makeEuroparlLineFile.py source code file:

my book on functional programming


new blog posts


Copyright 1998-2019 Alvin Alexander, alvinalexander.com
All Rights Reserved.

A percentage of advertising revenue from
pages under the /java/jwarehouse URI on this website is
paid back to open source projects.