APPROVE COMMIT NOTE: This patch has been committed # HG changeset patch # User Aidan Kehoe <kehoea(a)parhasard.net&gt; # Date 1524829819 -3600 # Fri Apr 27 12:50:19 2018 +0100 # Node ID fd1fdfb2c336c61478e7a2ca0cd98ebab06a54d9 # Parent 06e4b596dc40844bb53645fbf12cffa40d7922a7 Remove lib-src/make-case-conv.py definitively. lib-src/ChangeLog addition: 2018-04-27 Aidan Kehoe <kehoea(a)parhasard.net&gt; * make-case-conv.py: Remove this file, replaced by lisp/mule/make-case-conv.el diff -r 06e4b596dc40 -r fd1fdfb2c336 lib-src/ChangeLog --- a/lib-src/ChangeLog Wed Apr 25 21:49:16 2018 +0100 +++ b/lib-src/ChangeLog Fri Apr 27 12:50:19 2018 +0100 ＠＠ -1,3 +1,8 ＠＠ +2018-04-27 Aidan Kehoe <kehoea(a)parhasard.net&gt; + + * make-case-conv.py: + Remove this file, replaced by lisp/mule/make-case-conv.el + 2017-11-09 Aidan Kehoe <kehoea(a)parhasard.net&gt; * make-case-conv.py: diff -r 06e4b596dc40 -r fd1fdfb2c336 lib-src/make-case-conv.py --- a/lib-src/make-case-conv.py Wed Apr 25 21:49:16 2018 +0100 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 ＠＠ -1,208 +0,0 ＠＠ -#!/usr/bin/python - -### make-case-conv.py --- generate case-conversion info from the Unicode database - -## Copyright (C) 2010 Ben Wing. - -## Author: Ben Wing <ben(a)xemacs.org&gt; -## Maintainer: Ben Wing <ben(a)xemacs.org&gt; -## Current Version: 1.0, January 25, 2010 - -## This file is part of XEmacs. - -## XEmacs is free software; you can redistribute it and/or modify it -## under the terms of the GNU General Public License as published by -## the Free Software Foundation; either version 2, or (at your option) -## any later version. - -## XEmacs is distributed in the hope that it will be useful, but -## WITHOUT ANY WARRANTY; without even the implied warranty of -## MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU -## General Public License for more details. - -## You should have received a copy of the GNU General Public License -## along with XEmacs; see the file COPYING. If not, write to the Free -## Software Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA -## 02111-1307, USA. - -### Commentary: - -# This file parses the file CaseFolding.txt in Unicode's UNIDATA package, -# and generates a Lisp file containing instructions to set all the case -# mappings in the standard case table. - -# To run this file, redirect its stdout to the file mule/uni-case-conv.el -# (or whatever else you have named it according to the variable -# `output_filename'). - -# #### Aidan Kehoe, Do 9 Nov 2017 21:32:14 GMT; this approach doesn't work, -# since CaseFolding folds both upper and lower case characters to lower case, -# without marking which is which. We need to parse UnicodeData.txt instead; I -# do this in lisp/mule/make-case-conv.el. I will remove make-case-conv.py down -# the line. - -### Code: - -import urllib2, re, sys -#import fileinput - -# The URL holding the case-folding table at www.unicode.org. -uni_casefold_url = 'http://www.unicode.org/Public/UNIDATA/CaseFolding.txt' - -# Path to this file, as will appear in the comments of the generated file -our_filepath = 'lib-src/make-case-conv.py' - -# Name of the generated file (no directories in it) -output_filename = 'uni-case-conv.el' - -def argformat(format, arg): - if type(format) is str: - return format % arg - else: - return str(format) - -# Write formatted arguments to stdout. -def outout(format, *arg): - sys.stdout.write(argformat(format, arg)) - -# Write formatted arguments to stderr. -def errout(format, *arg): - sys.stderr.write(argformat(format, arg)) - - - -print """\ -;;; %s --- Case-conversion support for Unicode - -;; Copyright (C) 2010 Ben Wing. - -;; Keywords: multilingual, case, uppercase, lowercase, Unicode - -;; This file is part of XEmacs. - -;; XEmacs is free software; you can redistribute it and/or modify it -;; under the terms of the GNU General Public License as published by -;; the Free Software Foundation; either version 2, or (at your option) -;; any later version. - -;; XEmacs is distributed in the hope that it will be useful, but -;; WITHOUT ANY WARRANTY; without even the implied warranty of -;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU -;; General Public License for more details. - -;; You should have received a copy of the GNU General Public License -;; along with XEmacs; see the file COPYING. If not, write to the Free -;; Software Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA -;; 02111-1307, USA. - -;;; Commentary: - -;; DO NOT MODIFY THIS FILE!!!!!!!!!!!!!!!! -;; This file is autogenerated by %s. Modify that -;; file instead. - -;;; Code: - -;; Hack: We nreverse the table below before applying it so that the more -;; desirable mappings, which come early, override less desirable later ones. -;; In particular, we definitely do not want the following bindings to work -;; both ways: - -;; (?\u017F ?\u0073) ;; LATIN SMALL LETTER LONG S -;; (?\u212A ?\u006B) ;; KELVIN SIGN -;; (?\u212B ?\u00E5) ;; ANGSTROM SIGN - -;; The first two are especially bad as they will cause upcasing operations -;; on lowercase s and k to give strange results. It's actually worse than -;; that -- for unknown reasons, with the bad mappings in place, the byte- -;; compiler produces broken code for some files, which results in a stack- -;; underflow crash upon loadup in preparation for dumping. - -(loop - for (upper lower) - in (nreverse - '( -""" % (output_filename, our_filepath), - -#for line in fileinput.input(): -for line in urllib2.urlopen(uni_casefold_url): - - # Save original line - saveline = line - - # Save comment then remove it - m = re.match(r'.*#\s*(.*)', line) - if m: - comment = m.group(1) - else: - comment = '' - line = re.sub('#.*', '', line) - - # Strip whitespace; if line blank, do next one - line = line.strip() - if not line: - continue - - if re.match(r'([0-9A-F]+); F; (([0-9A-F]+)( [0-9A-F]+)*);$', line): - errout("Warning: Can't handle full mapping: %s", saveline) - outout(";;; WARNING: Unhandled full mapping:\n;;; %s", saveline) - continue - if re.match(r'([0-9A-F]+); T; ([0-9A-F]+);$', line): - errout("Warning: Can't handle Turkish mapping: %s", saveline) - outout(";;; WARNING: Unhandled Turkish mapping:\n;;; %s", - saveline) - continue - m = re.match(r'([0-9A-F]+); [CS]; ([0-9A-F]+);$', line) - if not m: - errout("Warning: Unrecognized line: %s", saveline) - outout(";;; WARNING: Unrecognized line:\n;;; %s", saveline) - continue - - def tounichar(val): - if val <= 0xFFFF: - return r'?\u%04X' % val - else: - return r'?\U%08X' % val - upper = tounichar(int(m.group(1), 16)) - lower = tounichar(int(m.group(2), 16)) - print r' (%s %s) ;; %s' % (upper, lower, comment) - -print """\ - )) - with case-table = (standard-case-table) - do - (put-case-table-pair upper lower case-table)) - -(provide '%s) - -;;; %s ends here""" % (output_filename.replace(".el",""), output_filename) - -## Another version, trying to diagnose byte-compiler underflow error caused -## by these additions -#print """\ -# ) -# with case-table = (standard-case-table) -# do -# (let* ((existing-lower (get-case-table 'downcase upper case-table)) -# (existing-lower (and (not (eq existing-lower upper)) existing-lower))) -# ;;(when (not (eq (char-charset lower) (char-charset upper))) -# ;; (princ (format "Upper %s (%s) not same charset as lower %s (%s)" upper (char-charset upper) lower (char-charset lower)))) -# (cond ((eq existing-lower lower) -# ;;(princ (format "Already seen mapping %s for char %s" lower upper)) -# ) -# (existing-lower -# ;;(princ (format "Existing mapping for char %s is %s, different from new %s?" upper existing-lower lower)) -# ) -# ((and (not (featurep 'unicode-internal)) -# (not (eq (char-charset lower) (char-charset upper)))) -# ;;(princ (format "Not adding cross-charset mapping %s -> %s" upper lower)) -# ) -# (t -# ;;(princ (format "Adding mapping for upper %s -> lower %s" upper lower)) -# (put-case-table-pair upper lower case-table) -# )))) -#""" -#print """\ -#(provide '%s) -# -#;;; %s ends here""" % (output_filename.replace(".el",""), output_filename) -- ‘As I sat looking up at the Guinness ad, I could never figure out / How your man stayed up on the surfboard after forty pints of stout’ (C. Moore)