[tools] Print unicode links on gen-* tools output

As Behdad's review
This commit is contained in:
Ebrahim Byagowi 2020-02-10 17:19:23 +03:30
parent 4dc87365d7
commit 6a390df8af
6 changed files with 32 additions and 27 deletions

View File

@ -1,16 +1,17 @@
#!/usr/bin/env python
# Input files:
# - https://unicode.org/Public/12.0.0/ucd/ArabicShaping.txt
# - https://unicode.org/Public/12.0.0/ucd/UnicodeData.txt
# - https://unicode.org/Public/12.0.0/ucd/Blocks.txt
from __future__ import print_function, division, absolute_import
import io, os.path, sys
if len (sys.argv) != 4:
print ("usage: ./gen-arabic-table.py ArabicShaping.txt UnicodeData.txt Blocks.txt", file=sys.stderr)
print ("""usage: ./gen-arabic-table.py ArabicShaping.txt UnicodeData.txt Blocks.txt
Input files, as of Unicode 12:
* https://unicode.org/Public/UCD/latest/ucd/ArabicShaping.txt
* https://unicode.org/Public/UCD/latest/ucd/UnicodeData.txt
* https://unicode.org/Public/UCD/latest/ucd/Blocks.txt
""", file=sys.stderr)
sys.exit (1)
files = [io.open (x, encoding='utf-8') for x in sys.argv[1:]]

View File

@ -1,7 +1,5 @@
#!/usr/bin/python
# Input file: https://www.unicode.org/Public/emoji/12.0/emoji-data.txt
from __future__ import print_function, division, absolute_import
import sys
import os.path
@ -9,7 +7,10 @@ from collections import OrderedDict
import packTab
if len (sys.argv) != 2:
print("usage: ./gen-emoji-table.py emoji-data.txt", file=sys.stderr)
print("""usage: ./gen-emoji-table.py emoji-data.txt
Input file, as of Unicode 12:
* https://www.unicode.org/Public/emoji/12.0/emoji-data.txt""", file=sys.stderr)
sys.exit (1)
f = open(sys.argv[1])

View File

@ -1,16 +1,16 @@
#!/usr/bin/env python
# Input files:
# - https://unicode.org/Public/12.0.0/ucd/IndicSyllabicCategory.txt
# - https://unicode.org/Public/12.0.0/ucd/IndicPositionalCategory.txt
# - https://unicode.org/Public/12.0.0/ucd/Blocks.txt
from __future__ import print_function, division, absolute_import
import io, sys
if len (sys.argv) != 4:
print ("usage: ./gen-indic-table.py IndicSyllabicCategory.txt IndicPositionalCategory.txt Blocks.txt", file=sys.stderr)
print ("""usage: ./gen-indic-table.py IndicSyllabicCategory.txt IndicPositionalCategory.txt Blocks.txt
Input files, as of Unicode 12:
* https://unicode.org/Public/UCD/latest/ucd/IndicSyllabicCategory.txt
* https://unicode.org/Public/UCD/latest/ucd/IndicPositionalCategory.txt
* https://unicode.org/Public/UCD/latest/ucd/Blocks.txt""", file=sys.stderr)
sys.exit (1)
ALLOWED_SINGLES = [0x00A0, 0x25CC]

View File

@ -1,7 +1,5 @@
#!/usr/bin/env python
# Input file: http://unicode.org/Public/UCD/latest/ucdxml/ucd.nounihan.grouped.zip
from __future__ import print_function, division, absolute_import
import io, os.path, sys, re
@ -9,7 +7,10 @@ import logging
logging.basicConfig(format='%(levelname)s: %(message)s', level=logging.INFO)
if len (sys.argv) not in (2, 3):
print("usage: ./gen-ucd-table ucd.nounihan.grouped.xml [/path/to/hb-common.h]", file=sys.stderr)
print("""usage: ./gen-ucd-table ucd.nounihan.grouped.xml [/path/to/hb-common.h]
Input file, as of Unicode 12:
* https://unicode.org/Public/UCD/latest/ucdxml/ucd.nounihan.grouped.zip""", file=sys.stderr)
sys.exit(1)
# https://github.com/harfbuzz/packtab

View File

@ -1,19 +1,19 @@
#!/usr/bin/env python
# flake8: noqa
# Input files:
# - https://unicode.org/Public/12.0.0/ucd/IndicSyllabicCategory.txt
# - https://unicode.org/Public/12.0.0/ucd/IndicPositionalCategory.txt
# - https://unicode.org/Public/12.0.0/ucd/UnicodeData.txt
# - https://unicode.org/Public/12.0.0/ucd/Blocks.txt
from __future__ import print_function, division, absolute_import
import io
import sys
if len (sys.argv) != 5:
print ("usage: ./gen-use-table.py IndicSyllabicCategory.txt IndicPositionalCategory.txt UnicodeData.txt Blocks.txt", file=sys.stderr)
print ("""usage: ./gen-use-table.py IndicSyllabicCategory.txt IndicPositionalCategory.txt UnicodeData.txt Blocks.txt
Input file, as of Unicode 12:
* https://unicode.org/Public/UCD/latest/ucd/IndicSyllabicCategory.txt
* https://unicode.org/Public/UCD/latest/ucd/IndicPositionalCategory.txt
* https://unicode.org/Public/UCD/latest/ucd/UnicodeData.txt
* https://unicode.org/Public/UCD/latest/ucd/Blocks.txt""", file=sys.stderr)
sys.exit (1)
BLACKLISTED_BLOCKS = ["Thai", "Lao"]

View File

@ -7,7 +7,6 @@ circles into sequences prohibited by the USE script development spec.
This function should be used as the ``preprocess_text`` of an
``hb_ot_complex_shaper_t``.
Input file: https://unicode.org/Public/12.0.0/ucd/Scripts.txt
"""
from __future__ import absolute_import, division, print_function, unicode_literals
@ -27,7 +26,10 @@ import io
import sys
if len (sys.argv) != 3:
print ('usage: ./gen-vowel-constraints.py ms-use/IndicShapingInvalidCluster.txt Scripts.txt', file=sys.stderr)
print ("""usage: ./gen-vowel-constraints.py ms-use/IndicShapingInvalidCluster.txt Scripts.txt
Input file, as of Unicode 12:
* https://unicode.org/Public/UCD/latest/ucd/Scripts.txt""", file=sys.stderr)
sys.exit (1)
with io.open (sys.argv[2], encoding='utf-8') as f: