def make_ninja_deps(rules_filename, out=sys.stdout):
"""
Output a complete Ninja file describing how to build the wordfreq data.
"""
print(HEADER, file=out)
# Copy in the rules section
with open(rules_filename, encoding='utf-8') as rulesfile:
print(rulesfile.read(), file=out)
lines = []
# The first dependency is to make sure the build file is up to date.
add_dep(lines, 'build_deps', 'rules.ninja', 'build.ninja',
extra='wordfreq_builder/ninja.py')
lines.extend(itertools.chain(
twitter_deps(
data_filename('raw-input/twitter/all-2014.txt'),
slice_prefix=data_filename('slices/twitter/tweets-2014'),
combined_prefix=data_filename('generated/twitter/tweets-2014'),
slices=40,
languages=CONFIG['sources']['twitter']
),
wikipedia_deps(
data_filename('raw-input/wikipedia'),
CONFIG['sources']['wikipedia']
),
google_books_deps(
data_filename('raw-input/google-books')
),
leeds_deps(
data_filename('source-lists/leeds'),
CONFIG['sources']['leeds']
),
opensubtitles_deps(
data_filename('source-lists/opensubtitles'),
CONFIG['sources']['opensubtitles']
),
subtlex_en_deps(
data_filename('source-lists/subtlex'),
CONFIG['sources']['subtlex-en']
),
subtlex_other_deps(
data_filename('source-lists/subtlex'),
CONFIG['sources']['subtlex-other']
),
jieba_deps(
data_filename('source-lists/jieba'),
CONFIG['sources']['jieba']
),
combine_lists(all_languages())
))
print('\n'.join(lines), file=out)
def make_ninja_deps(rules_filename, out=sys.stdout):
"""
Output a complete Ninja file describing how to build the wordfreq data.
"""
print(HEADER, file=out)
# Copy in the rules section
with open(rules_filename, encoding="utf-8") as rulesfile:
print(rulesfile.read(), file=out)
lines = []
# The first dependency is to make sure the build file is up to date.
add_dep(lines, "build_deps", "rules.ninja", "build.ninja", extra="wordfreq_builder/ninja.py")
lines.extend(
twitter_deps(
data_filename("raw-input/twitter/all-2014.txt"),
slice_prefix=data_filename("slices/twitter/tweets-2014"),
combined_prefix=data_filename("generated/twitter/tweets-2014"),
slices=40,
languages=CONFIG["sources"]["twitter"],
)
)
lines.extend(wikipedia_deps(data_filename("raw-input/wikipedia"), CONFIG["sources"]["wikipedia"]))
lines.extend(google_books_deps(data_filename("raw-input/google-books")))
lines.extend(leeds_deps(data_filename("source-lists/leeds"), CONFIG["sources"]["leeds"]))
lines.extend(opensubtitles_deps(data_filename("source-lists/opensubtitles"), CONFIG["sources"]["opensubtitles"]))
lines.extend(combine_lists(all_languages()))
print("\n".join(lines), file=out)
def make_ninja_deps(rules_filename, out=sys.stdout):
"""
Output a complete Ninja file describing how to build the wordfreq data.
"""
print(HEADER, file=out)
# Copy in the rules section
with open(rules_filename, encoding='utf-8') as rulesfile:
print(rulesfile.read(), file=out)
lines = []
# The first dependency is to make sure the build file is up to date.
add_dep(lines,
'build_deps',
'rules.ninja',
'build.ninja',
extra='wordfreq_builder/ninja.py')
lines.extend(
twitter_deps(
data_filename('raw-input/twitter/all-2014.txt'),
slice_prefix=data_filename('slices/twitter/tweets-2014'),
combined_prefix=data_filename('generated/twitter/tweets-2014'),
slices=40,
languages=CONFIG['sources']['twitter']))
lines.extend(
wikipedia_deps(data_filename('raw-input/wikipedia'),
CONFIG['sources']['wikipedia']))
lines.extend(google_books_deps(data_filename('raw-input/google-books')))
lines.extend(
leeds_deps(data_filename('source-lists/leeds'),
CONFIG['sources']['leeds']))
lines.extend(
opensubtitles_deps(data_filename('source-lists/opensubtitles'),
CONFIG['sources']['opensubtitles']))
lines.extend(combine_lists(all_languages()))
print('\n'.join(lines), file=out)
from wordfreq_builder.config import (CONFIG, data_filename, wordlist_filename,
all_languages, source_names)
import sys
import pathlib
HEADER = """# This file is automatically generated. Do not edit it.
# You can regenerate it using the 'wordfreq-build-deps' command.
"""
TMPDIR = data_filename('tmp')
def add_dep(lines, rule, input, output, extra=None, params=None):
if isinstance(output, list):
output = ' '.join(output)
if isinstance(input, list):
input = ' '.join(input)
if extra:
if isinstance(extra, list):
extra = ' '.join(extra)
extrastr = ' | ' + extra
else:
extrastr = ''
build_rule = "build {output}: {rule} {input}{extra}".format(output=output,
rule=rule,
input=input,
extra=extrastr)
lines.append(build_rule)
if params:
for key, val in params.items():
lines.append(" {key} = {val}".format(key=key, val=val))
lines.append("")
from wordfreq_builder.config import (
CONFIG, data_filename, wordlist_filename, all_languages, source_names
)
import sys
import pathlib
import itertools
HEADER = """# This file is automatically generated. Do not edit it.
# You can change its behavior by editing wordfreq_builder/ninja.py,
# and regenerate it by running 'make'.
"""
TMPDIR = data_filename('tmp')
def add_dep(lines, rule, input, output, extra=None, params=None):
if isinstance(output, list):
output = ' '.join(output)
if isinstance(input, list):
input = ' '.join(input)
if extra:
if isinstance(extra, list):
extra = ' '.join(extra)
extrastr = ' | ' + extra
else:
extrastr = ''
build_rule = "build {output}: {rule} {input}{extra}".format(
output=output, rule=rule, input=input, extra=extrastr
)
lines.append(build_rule)
if params:
for key, val in params.items():
from wordfreq_builder.config import CONFIG, data_filename, wordlist_filename, all_languages, source_names
import sys
import pathlib
HEADER = """# This file is automatically generated. Do not edit it.
# You can regenerate it using the 'wordfreq-build-deps' command.
"""
TMPDIR = data_filename("tmp")
def add_dep(lines, rule, input, output, extra=None, params=None):
if isinstance(output, list):
output = " ".join(output)
if isinstance(input, list):
input = " ".join(input)
if extra:
if isinstance(extra, list):
extra = " ".join(extra)
extrastr = " | " + extra
else:
extrastr = ""
build_rule = "build {output}: {rule} {input}{extra}".format(output=output, rule=rule, input=input, extra=extrastr)
lines.append(build_rule)
if params:
for key, val in params.items():
lines.append(" {key} = {val}".format(key=key, val=val))
lines.append("")
def make_ninja_deps(rules_filename, out=sys.stdout):
"""
