File: get-wikimedia.sh

package info (click to toggle)
fasttext 0.9.2-3
  • links: PTS, VCS
  • area: main
  • in suites: bullseye, sid
  • size: 7,800 kB
  • sloc: javascript: 10,266; cpp: 5,458; python: 2,425; sh: 616; makefile: 102; xml: 81; perl: 43
file content (79 lines) | stat: -rwxr-xr-x 3,310 bytes parent folder | download
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
#!/usr/bin/env bash
#
# Copyright (c) 2016-present, Facebook, Inc.
# All rights reserved.
#
# This source code is licensed under the MIT license found in the
# LICENSE file in the root directory of this source tree.
#

set -e

normalize_text() {
    sed -e "s/’/'/g" -e "s/′/'/g" -e "s/''/ /g" -e "s/'/ ' /g" -e "s/“/\"/g" -e "s/”/\"/g" \
        -e 's/"/ " /g' -e 's/\./ \. /g' -e 's/<br \/>/ /g' -e 's/, / , /g' -e 's/(/ ( /g' -e 's/)/ ) /g' -e 's/\!/ \! /g' \
        -e 's/\?/ \? /g' -e 's/\;/ /g' -e 's/\:/ /g' -e 's/-/ - /g' -e 's/=/ /g' -e 's/=/ /g' -e 's/*/ /g' -e 's/|/ /g' \
        -e 's/«/ /g' | tr 0-9 " "
}

export LANGUAGE=en_US.UTF-8
export LC_ALL=en_US.UTF-8
export LANG=en_US.UTF-8

NOW=$(date +"%Y%m%d")

ROOT="data/wikimedia/${NOW}"
mkdir -p "${ROOT}"
echo "Saving data in ""$ROOT"
read -r -p "Choose a language (e.g. en, bh, fr, etc.): " choice
LANG="$choice"
echo "Chosen language: ""$LANG"
read -r -p "Continue to download (WARNING: This might be big and can take a long time!)(y/n)? " choice
case "$choice" in
  y|Y ) echo "Starting download...";;
  n|N ) echo "Exiting";exit 1;;
  * ) echo "Invalid answer";exit 1;;
esac
wget -c "https://dumps.wikimedia.org/""$LANG""wiki/latest/""${LANG}""wiki-latest-pages-articles.xml.bz2" -P "${ROOT}"
echo "Processing ""$ROOT"/"$LANG""wiki-latest-pages-articles.xml.bz2"
bzip2 -c -d "$ROOT"/"$LANG""wiki-latest-pages-articles.xml.bz2" | awk '{print tolower($0);}' | perl -e '
# Program to filter Wikipedia XML dumps to "clean" text consisting only of lowercase
# letters (a-z, converted from A-Z), and spaces (never consecutive)...
# All other characters are converted to spaces.  Only text which normally appears.
# in the web browser is displayed.  Tables are removed.  Image captions are.
# preserved.  Links are converted to normal text.  Digits are spelled out.
# *** Modified to not spell digits or throw away non-ASCII characters ***
# Written by Matt Mahoney, June 10, 2006.  This program is released to the public domain.
$/=">";                     # input record separator
while (<>) {
  if (/<text /) {$text=1;}  # remove all but between <text> ... </text>
  if (/#redirect/i) {$text=0;}  # remove #REDIRECT
  if ($text) {
    # Remove any text not normally visible
    if (/<\/text>/) {$text=0;}
    s/<.*>//;               # remove xml tags
    s/&amp;/&/g;            # decode URL encoded chars
    s/&lt;/</g;
    s/&gt;/>/g;
    s/<ref[^<]*<\/ref>//g;  # remove references <ref...> ... </ref>
    s/<[^>]*>//g;           # remove xhtml tags
    s/\[http:[^] ]*/[/g;    # remove normal url, preserve visible text
    s/\|thumb//ig;          # remove images links, preserve caption
    s/\|left//ig;
    s/\|right//ig;
    s/\|\d+px//ig;
    s/\[\[image:[^\[\]]*\|//ig;
    s/\[\[category:([^|\]]*)[^]]*\]\]/[[$1]]/ig;  # show categories without markup
    s/\[\[[a-z\-]*:[^\]]*\]\]//g;  # remove links to other languages
    s/\[\[[^\|\]]*\|/[[/g;  # remove wiki url, preserve visible text
    s/{{[^}]*}}//g;         # remove {{icons}} and {tables}
    s/{[^}]*}//g;
    s/\[//g;                # remove [ and ]
    s/\]//g;
    s/&[^;]*;/ /g;          # remove URL encoded chars
    $_=" $_ ";
    chop;
    print $_;
  }
}
' | normalize_text | awk '{if (NF>1) print;}' | tr -s " " | shuf > "${ROOT}"/wiki."${LANG}".txt