wordfreq/wordfreq_builder/rules.ninja

# 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 = mkdir -p $$(dirname $out) && bunzip2 -c $in | wiki2text > $out

# The wiki2tokens rule is the same as the wiki2text rule, but uses the -t
# flag to tell the Nim code to output one token per line (according to its
# language-agnostic tokenizer, which splits on punctuation and whitespace in
# basically the same way as wordfreq).
#
# The fact that this uses a language-agnostic tokenizer means it should not
# be applied to Chinese or Japanese.
rule wiki2tokens
  command = mkdir -p $$(dirname $out) && bunzip2 -c $in | wiki2text -t > $out

# To tokenize Japanese, we run it through Mecab and take the first column.
# We don't have a plan for tokenizing Chinese yet.
rule tokenize_japanese
  command = mkdir -p $$(dirname $out) && mecab -b 1048576 < $in | cut -f 1 | grep -v "EOS" > $out

# Tokenizing text from Twitter generally requires us to use a more powerful
# tokenizer than the language-agnostic one.
#
# Our usual build process does not use this step. It just assumes it's already
# done, because it takes a very long time. This is what the 'data/intermediate'
# directory contains.
rule tokenize_twitter
  command = mkdir -p $$(dirname $prefix) && python -m wordfreq_builder.cli.pretokenize_twitter $in $prefix

# Convert the output of tokenize_twitter into the form used by wiki2tokens,
# by inserting line breaks between tokens, and removing things that appear
# to be URLs or usernames.
#
# I could have output it this way in the first place, but the fact is that I
# didn't. Writing this rule to fix it was easier than re-doing three days of
# computation.
rule format_twitter
  command = mkdir -p $$(dirname $out) && python -m wordfreq_builder.cli.format_twitter $in $out

# 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 = mkdir -p $$(dirname $out) && 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 = mkdir -p $$(dirname $out) && tr ' ' ',' < $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 = mkdir -p $$(dirname $out) && zcat $in | cut -f 1,3 | grep -v '[,"]' | sed -rn 's/(.*)\s(...+)/\1,\2/p' > $out

rule count
  command = mkdir -p $$(dirname $out) && python -m wordfreq_builder.cli.count_tokens $in $out

rule merge
  command = mkdir -p $$(dirname $out) && python -m wordfreq_builder.cli.combine_lists -o $out $in

rule freqs2dB
  command = mkdir -p $$(dirname $out) && python -m wordfreq_builder.cli.freqs_to_dB $in $out

rule cat
  command = cat $in > $out