minor, move scripts manuals to __doc__

src/gen-arabic-table.py

@@ -1,15 +1,17 @@
 #!/usr/bin/env python3
 
-import io, os.path, sys
+"""usage: ./gen-arabic-table.py ArabicShaping.txt UnicodeData.txt Blocks.txt
-
-if len (sys.argv) != 4:
-	print ("""usage: ./gen-arabic-table.py ArabicShaping.txt UnicodeData.txt Blocks.txt
 
 Input files:
 * 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)
+"""
+
+import io, os.path, sys
+
+if len (sys.argv) != 4:
+	print (__doc__, file=sys.stderr)
 	sys.exit (1)
 
 files = [io.open (x, encoding='utf-8') for x in sys.argv[1:]]
@@ -126,7 +128,7 @@ def print_joining_table(f):
 	print ("}; /* Table items: %d; occupancy: %d%% */" % (offset, occupancy))
 	print ()
 
-	page_bits = 12;
+	page_bits = 12
 	print ()
 	print ("static unsigned int")
 	print ("joining_type (hb_codepoint_t u)")

src/gen-def.py

@@ -1,9 +1,11 @@
 #!/usr/bin/env python3
 
+"usage: gen-def.py harfbuzz.def hb.h [hb-blob.h hb-buffer.h ...]"
+
 import io, os, re, sys
 
 if len (sys.argv) < 3:
-	sys.exit("usage: gen-def.py harfbuzz.def hb.h [hb-blob.h hb-buffer.h ...]")
+	sys.exit(__doc__)
 
 output_file = sys.argv[1]
 header_paths = sys.argv[2:]

src/gen-emoji-table.py

@@ -1,15 +1,18 @@
 #!/usr/bin/env python3
 
+"""usage: ./gen-emoji-table.py emoji-data.txt
+
+Input file:
+* https://www.unicode.org/Public/UCD/latest/ucd/emoji/emoji-data.txt
+"""
+
 import sys
 import os.path
 from collections import OrderedDict
 import packTab
 
 if len (sys.argv) != 2:
-	print("""usage: ./gen-emoji-table.py emoji-data.txt
+	print(__doc__, file=sys.stderr)
-
-Input file:
-* https://www.unicode.org/Public/UCD/latest/ucd/emoji/emoji-data.txt""", file=sys.stderr)
 	sys.exit (1)
 
 f = open(sys.argv[1])

src/gen-harfbuzzcc.py

@@ -1,9 +1,11 @@
 #!/usr/bin/env python3
 
+"usage: gen-harfbuzzcc.py harfbuzz.cc hb-blob.cc hb-buffer.cc ..."
+
 import io, os, re, sys
 
 if len (sys.argv) < 3:
-	sys.exit("usage: gen-harfbuzzcc.py harfbuzz.def hb-blob.cc hb-buffer.cc ...")
+	sys.exit(__doc__)
 
 output_file = sys.argv[1]
 source_paths = sys.argv[2:]

src/gen-hb-version.py

@@ -1,9 +1,11 @@
 #!/usr/bin/env python3
 
+"usage: gen-hb-version.py 1.0.0 hb-version.h.in hb-version.h"
+
 import io, os, re, sys
 
 if len (sys.argv) < 4:
-	sys.exit("usage: gen-hb-version.py 1.0.0 hb-version.h.in hb-version.h")
+	sys.exit(__doc__)
 
 version = sys.argv[1]
 major, minor, micro = version.split (".")

src/gen-indic-table.py

@@ -1,14 +1,17 @@
 #!/usr/bin/env python3
 
-import io, sys
+"""usage: ./gen-indic-table.py IndicSyllabicCategory.txt IndicPositionalCategory.txt Blocks.txt
-
-if len (sys.argv) != 4:
-	print ("""usage: ./gen-indic-table.py IndicSyllabicCategory.txt IndicPositionalCategory.txt Blocks.txt
 
 Input files:
 * 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)
+* https://unicode.org/Public/UCD/latest/ucd/Blocks.txt
+"""
+
+import io, sys
+
+if len (sys.argv) != 4:
+	print (__doc__, file=sys.stderr)
 	sys.exit (1)
 
 ALLOWED_SINGLES = [0x00A0, 0x25CC]

src/gen-os2-unicode-ranges.py

@@ -1,8 +1,9 @@
 #!/usr/bin/env python3
 
-# Generates the code for a sorted unicode range array as used in hb-ot-os2-unicode-ranges.hh
+"""Generates the code for a sorted unicode range array as used in hb-ot-os2-unicode-ranges.hh
-# Input is a tab seperated list of unicode ranges from the otspec
+Input is a tab seperated list of unicode ranges from the otspec
-# (https://docs.microsoft.com/en-us/typography/opentype/spec/os2#ur).
+(https://docs.microsoft.com/en-us/typography/opentype/spec/os2#ur).
+"""
 
 import io
 import re
@@ -17,7 +18,7 @@ input_file = args[0]
 
 with io.open(input_file, mode="r", encoding="utf-8") as f:
 
-  all_ranges = [];
+  all_ranges = []
   current_bit = 0
   while True:
     line = f.readline().strip()

src/gen-tag-table.py

@@ -16,6 +16,12 @@ back to BCP 47 tags. Ambiguous OpenType tags (those that correspond to
 multiple BCP 47 tags) are listed here, except when the alphabetically
 first BCP 47 tag happens to be the chosen disambiguated tag. In that
 case, the fallback behavior will choose the right tag anyway.
+
+usage: ./gen-tag-table.py languagetags language-subtag-registry
+
+Input files:
+* https://docs.microsoft.com/en-us/typography/opentype/spec/languagetags
+* https://www.iana.org/assignments/language-subtag-registry/language-subtag-registry
 """
 
 import collections
@@ -30,11 +36,7 @@ import sys
 import unicodedata
 
 if len (sys.argv) != 3:
-	print ('''usage: ./gen-tag-table.py languagetags language-subtag-registry
+	print (__doc__, file=sys.stderr)
-
-Input files:
-* https://docs.microsoft.com/en-us/typography/opentype/spec/languagetags
-* https://www.iana.org/assignments/language-subtag-registry/language-subtag-registry''', file=sys.stderr)
 	sys.exit (1)
 
 from html import unescape

src/gen-ucd-table.py

@@ -1,14 +1,17 @@
 #!/usr/bin/env python3
 
+"""usage: ./gen-ucd-table ucd.nounihan.grouped.xml [/path/to/hb-common.h]
+
+Input file:
+* https://unicode.org/Public/UCD/latest/ucdxml/ucd.nounihan.grouped.zip
+"""
+
 import io, os.path, sys, re
 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]
+	print(__doc__, file=sys.stderr)
-
-Input file:
-* https://unicode.org/Public/UCD/latest/ucdxml/ucd.nounihan.grouped.zip""", file=sys.stderr)
 	sys.exit(1)
 
 # https://github.com/harfbuzz/packtab

src/gen-use-table.py

@@ -1,17 +1,20 @@
 #!/usr/bin/env python3
-# flake8: noqa
+# flake8: noqa: F821
 
-import io
+"""usage: ./gen-use-table.py IndicSyllabicCategory.txt IndicPositionalCategory.txt UnicodeData.txt Blocks.txt
-import sys
-
-if len (sys.argv) != 5:
-	print ("""usage: ./gen-use-table.py IndicSyllabicCategory.txt IndicPositionalCategory.txt UnicodeData.txt Blocks.txt
 
 Input file:
 * 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)
+* https://unicode.org/Public/UCD/latest/ucd/Blocks.txt
+"""
+
+import io
+import sys
+
+if len (sys.argv) != 5:
+	print (__doc__, file=sys.stderr)
 	sys.exit (1)
 
 BLACKLISTED_BLOCKS = ["Thai", "Lao"]

src/gen-vowel-constraints.py

@@ -7,6 +7,10 @@ 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``.
 
+usage: ./gen-vowel-constraints.py ms-use/IndicShapingInvalidCluster.txt Scripts.txt
+
+Input file:
+* https://unicode.org/Public/UCD/latest/ucd/Scripts.txt
 """
 
 import collections
@@ -19,10 +23,7 @@ import io
 import sys
 
 if len (sys.argv) != 3:
-	print ("""usage: ./gen-vowel-constraints.py ms-use/IndicShapingInvalidCluster.txt Scripts.txt
+	print (__doc__, file=sys.stderr)
-
-Input file:
-* 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: