mirror of
https://github.com/rspeer/wordfreq.git
synced 2024-12-24 18:01:38 +00:00
102 lines
4.0 KiB
Plaintext
102 lines
4.0 KiB
Plaintext
# This defines the rules on how to build parts of the wordfreq lists, using the
|
|
# Ninja build system:
|
|
#
|
|
# http://martine.github.io/ninja/manual.html
|
|
#
|
|
# Ninja is available in the 'ninja-build' Ubuntu package. It's like make with
|
|
# better parallelism and the ability for build steps to produce multiple
|
|
# outputs. The tradeoff is that its rule syntax isn't full of magic for
|
|
# expanding wildcards and finding dependencies, so in general you have to
|
|
# write the dependencies using a script.
|
|
#
|
|
# This file will become the header of the larger build.ninja file, which also
|
|
# contains the programatically-defined dependency graph.
|
|
|
|
# Variables
|
|
DATA = ./data
|
|
|
|
# How to build the build.ninja file itself. (Use the Makefile to get it the
|
|
# first time.)
|
|
rule build_deps
|
|
command = python -m wordfreq_builder.cli.build_deps $in > $out
|
|
|
|
# Splits the single file $in into $slices parts, whose names will be
|
|
# $prefix plus a two-digit numeric suffix.
|
|
rule split
|
|
command = mkdir -p $$(dirname $prefix) && split -d -n r/$slices $in $prefix
|
|
|
|
# wiki2text is a tool I wrote using Nim 0.11, which extracts plain text from
|
|
# Wikipedia dumps obtained from dumps.wikimedia.org. The code is at
|
|
# https://github.com/rspeer/wiki2text.
|
|
rule wiki2text
|
|
command = bunzip2 -c $in | wiki2text > $out
|
|
|
|
# To tokenize Japanese, we run it through Mecab and take the first column.
|
|
rule tokenize_japanese
|
|
command = mecab -b 1048576 < $in | cut -f 1 | grep -v "EOS" > $out
|
|
|
|
# Process Chinese by converting all Traditional Chinese characters to
|
|
# Simplified equivalents -- not because that's a good way to get readable
|
|
# text, but because that's how we're going to look them up.
|
|
rule simplify_chinese
|
|
command = python -m wordfreq_builder.cli.simplify_chinese < $in > $out
|
|
|
|
# Tokenizing text from Twitter requires us to language-detect and tokenize
|
|
# in the same step.
|
|
rule tokenize_twitter
|
|
command = mkdir -p $$(dirname $prefix) && python -m wordfreq_builder.cli.tokenize_twitter $in $prefix
|
|
|
|
# To convert the Leeds corpus, look for space-separated lines that start with
|
|
# an integer and a decimal. The integer is the rank, which we discard. The
|
|
# decimal is the frequency, and the remaining text is the term. Use sed -n
|
|
# with /p to output only lines where the match was successful.
|
|
#
|
|
# Grep out the term "EOS", an indication that Leeds used MeCab and didn't
|
|
# strip out the EOS lines.
|
|
rule convert_leeds
|
|
command = sed -rn 's/([0-9]+) ([0-9.]+) (.*)/\3,\2/p' < $in | grep -v 'EOS,' > $out
|
|
|
|
# To convert the OpenSubtitles frequency data, simply replace spaces with
|
|
# commas.
|
|
rule convert_opensubtitles
|
|
command = tr ' ' ',' < $in > $out
|
|
|
|
# To convert SUBTLEX, we take the 1st and Nth columns, strip the header,
|
|
# run it through ftfy, convert tabs to commas and spurious CSV formatting to
|
|
# and remove lines with unfixable half-mojibake.
|
|
rule convert_subtlex
|
|
command = cut -f $textcol,$freqcol $in | tail -n +$startrow | ftfy | tr ' ",' ', ' | grep -v 'â,' > $out
|
|
|
|
rule convert_jieba
|
|
command = cut -d ' ' -f 1,2 $in | grep -v '[,"]' | tr ' ' ',' > $out
|
|
|
|
rule counts_to_jieba
|
|
command = python -m wordfreq_builder.cli.counts_to_jieba $in $out
|
|
|
|
|
|
# Convert and clean up the Google Books Syntactic N-grams data. Concatenate all
|
|
# the input files, keep only the single words and their counts, and only keep
|
|
# lines with counts of 100 or more.
|
|
#
|
|
# (These will still be repeated as the word appears in different grammatical
|
|
# roles, information that the source data provides that we're discarding. The
|
|
# source data was already filtered to only show words in roles with at least
|
|
# two-digit counts of occurences.)
|
|
rule convert_google_syntactic_ngrams
|
|
command = zcat $in | cut -f 1,3 | grep -v '[,"]' | sed -rn 's/(.*)\s(...+)/\1,\2/p' > $out
|
|
|
|
rule count
|
|
command = python -m wordfreq_builder.cli.count_tokens $in $out
|
|
|
|
rule merge
|
|
command = python -m wordfreq_builder.cli.merge_freqs -o $out -c $cutoff -l $lang $in
|
|
|
|
rule merge_counts
|
|
command = python -m wordfreq_builder.cli.merge_counts -o $out $in
|
|
|
|
rule freqs2cB
|
|
command = python -m wordfreq_builder.cli.freqs_to_cB $lang $in $out
|
|
|
|
rule cat
|
|
command = cat $in > $out
|