Re: [PATCH] contrib: add unicode/utf8-dump.py
On 11/1/21 16:32, David Malcolm wrote: |Thanks. Here's an updated version of the script that fixes the above issues.| Thanks. Please install it (there are no strict approval rules for contrib folder). Cheers, Martin
[PATCH] contrib: add unicode/utf8-dump.py
On Mon, 2021-11-01 at 15:36 +0100, Martin Liška wrote: > On 11/1/21 15:14, David Malcolm via Gcc-patches wrote: > > > This script may be useful when debugging issues relating to > > > Unicode encoding (e.g. when investigating source files with > > > bidirectional control characters).| > > I like the script except the following flake8 issues: > > $ flake8 contrib/unicode/utf8-dump.py > contrib/unicode/utf8-dump.py:35:1: E302 expected 2 blank lines, found > 1 > contrib/unicode/utf8-dump.py:43:1: E302 expected 2 blank lines, found > 1 > contrib/unicode/utf8-dump.py:53:1: E302 expected 2 blank lines, found > 1 > contrib/unicode/utf8-dump.py:64:1: E305 expected 2 blank lines after > class or function definition, found 1 Thanks. Here's an updated version of the script that fixes the above issues. contrib/ChangeLog: * unicode/utf8-dump.py: New file. Signed-off-by: David Malcolm --- contrib/unicode/utf8-dump.py | 69 1 file changed, 69 insertions(+) create mode 100755 contrib/unicode/utf8-dump.py diff --git a/contrib/unicode/utf8-dump.py b/contrib/unicode/utf8-dump.py new file mode 100755 index 000..f12ee79f9f2 --- /dev/null +++ b/contrib/unicode/utf8-dump.py @@ -0,0 +1,69 @@ +#!/usr/bin/env python3 +# +# Script to dump a UTF-8 file as a list of numbered lines (mimicking GCC's +# diagnostic output format), interleaved with lines per character showing +# the Unicode codepoints, the UTF-8 encoding bytes, the name of the +# character, and, where printable, the characters themselves. +# The lines are printed in logical order, which may help the reader to grok +# the relationship between visual and logical ordering in bi-di files. +# +# SPDX-License-Identifier: MIT +# +# Copyright (C) 2021 David Malcolm . +# +# Permission is hereby granted, free of charge, to any person obtaining a +# copy of this software and associated documentation files (the "Software"), +# to deal in the Software without restriction, including without limitation +# the rights to use, copy, modify, merge, publish, distribute, sublicense, +# and/or sell copies of the Software, and to permit persons to whom the +# Software is furnished to do so, subject to the following conditions: +# +# The above copyright notice and this permission notice shall be included +# in all copies or substantial portions of the Software. +# +# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS +# OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF +# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. +# IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY +# CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT +# OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE +# OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. + +import sys +import unicodedata + + +def get_name(ch): +try: +return unicodedata.name(ch) +except ValueError: +if ch == '\n': +return 'LINE FEED (LF)' +return '(unknown)' + + +def get_printable(ch): +cat = unicodedata.category(ch) +if cat == 'Cc': +return '(control character)' +elif cat == 'Cf': +return '(format control)' +elif cat[0] == 'Z': +return '(separator)' +return ch + + +def dump_file(f_in): +line_num = 1 +for line in f_in: +print('%4i | %s' % (line_num, line.rstrip())) +for ch in line: +utf8_desc = '%15s' % (' '.join(['0x%02x' % b +for b in ch.encode('utf-8')])) +print('%4s | U+%04X %s %40s %s' + % ('', ord(ch), utf8_desc, get_name(ch), get_printable(ch))) +line_num += 1 + + +with open(sys.argv[1], mode='r') as f_in: +dump_file(f_in) -- 2.26.3
Re: [PATCH] contrib: add unicode/utf8-dump.py
On 11/1/21 15:14, David Malcolm via Gcc-patches wrote: |This script may be useful when debugging issues relating to Unicode encoding (e.g. when investigating source files with bidirectional control characters).| I like the script except the following flake8 issues: $ flake8 contrib/unicode/utf8-dump.py contrib/unicode/utf8-dump.py:35:1: E302 expected 2 blank lines, found 1 contrib/unicode/utf8-dump.py:43:1: E302 expected 2 blank lines, found 1 contrib/unicode/utf8-dump.py:53:1: E302 expected 2 blank lines, found 1 contrib/unicode/utf8-dump.py:64:1: E305 expected 2 blank lines after class or function definition, found 1 Martin
[PATCH] contrib: add unicode/utf8-dump.py
This script may be useful when debugging issues relating to Unicode encoding (e.g. when investigating source files with bidirectional control characters). It dump a UTF-8 file as a list of numbered lines (mimicking GCC's diagnostic output format), interleaved with lines per character showing the Unicode codepoints, the UTF-8 encoding bytes, the name of the character, and, where printable, the characters themselves. The lines are printed in logical order, which may help the reader to grok the relationship between visual and logical ordering in bi-di files. For example: $ cat test.c int གྷ; const char *אבג = "ALEF-BET-GIMEL"; $ ./contrib/unicode/utf8-dump.py test.c 1 | int གྷ; | U+00690x69 LATIN SMALL LETTER I i | U+006E0x6e LATIN SMALL LETTER N n | U+00740x74 LATIN SMALL LETTER T t | U+00200x20SPACE (separator) | U+0F43 0xe0 0xbd 0x83 TIBETAN LETTER GHA གྷ | U+003B0x3bSEMICOLON ; | U+000A0x0a LINE FEED (LF) (control character) 2 | const char *אבג = "ALEF-BET-GIMEL"; | U+00630x63 LATIN SMALL LETTER C c | U+006F0x6f LATIN SMALL LETTER O o | U+006E0x6e LATIN SMALL LETTER N n | U+00730x73 LATIN SMALL LETTER S s | U+00740x74 LATIN SMALL LETTER T t | U+00200x20SPACE (separator) | U+00630x63 LATIN SMALL LETTER C c | U+00680x68 LATIN SMALL LETTER H h | U+00610x61 LATIN SMALL LETTER A a | U+00720x72 LATIN SMALL LETTER R r | U+00200x20SPACE (separator) | U+002A0x2a ASTERISK * | U+05D0 0xd7 0x90 HEBREW LETTER ALEF א | U+05D1 0xd7 0x91HEBREW LETTER BET ב | U+05D2 0xd7 0x92 HEBREW LETTER GIMEL ג | U+00200x20SPACE (separator) | U+003D0x3d EQUALS SIGN = | U+00200x20SPACE (separator) | U+00220x22 QUOTATION MARK " | U+00410x41 LATIN CAPITAL LETTER A A | U+004C0x4c LATIN CAPITAL LETTER L L | U+00450x45 LATIN CAPITAL LETTER E E | U+00460x46 LATIN CAPITAL LETTER F F | U+002D0x2d HYPHEN-MINUS - | U+00420x42 LATIN CAPITAL LETTER B B | U+00450x45 LATIN CAPITAL LETTER E E | U+00540x54 LATIN CAPITAL LETTER T T | U+002D0x2d HYPHEN-MINUS - | U+00470x47 LATIN CAPITAL LETTER G G | U+00490x49 LATIN CAPITAL LETTER I I | U+004D0x4d LATIN CAPITAL LETTER M M | U+00450x45 LATIN CAPITAL LETTER E E | U+004C0x4c LATIN CAPITAL LETTER L L | U+00220x22 QUOTATION MARK " | U+003B0x3bSEMICOLON ; | U+000A0x0a LINE FEED (LF) (control character) Tested with Python 3.8 OK for trunk and to backport? contrib/ChangeLog: * unicode/utf8-dump.py: New file. Signed-off-by: David Malcolm --- contrib/unicode/utf8-dump.py | 65 1 file changed, 65 insertions(+) create mode 100755 contrib/unicode/utf8-dump.py diff --git a/contrib/unicode/utf8-dump.py b/contrib/unicode/utf8-dump.py new file mode 100755 index 000..21885a85bdc --- /dev/null +++ b/contrib/unicode/utf8-dump.py @@ -0,0 +1,65 @@ +#!/usr/bin/env python3 +# +# Script to dump a UTF-8 file as a list of numbered lines (mimicking GCC's +# diagnostic output format), interleaved with lines per character showing +# the Unicode codepoints, the UTF-8 encoding bytes, the name of the +# character, and, where printable, the characters themselves. +# The lines are printed in logical order, which may help the reader to grok +# the relationship between visual and logical ordering in