HTML Diff

From: Olivier Matz Date: Sun, 6 Jan 2013 16:11:04 +0000 (+0100) Subject: add utf-8 support X-Git-Tag: v1.0~4 X-Git-Url: http://git.droids-corp.org/?a=commitdiff_plain;h=0ca475f9e41664da1195d4582567d52be5ab24d8;p=diff2html.git add utf-8 support Signed-off-by: Scito Signed-off: Olivier Matz --- diff --git a/diff2html.py b/diff2html.py index 3e52700..dc000ee 100644 --- a/diff2html.py +++ b/diff2html.py @@ -1,4 +1,5 @@ #! /usr/bin/python +# coding=utf-8 # # This program is free software; you can redistribute it and/or modify # it under the terms of the GNU General Public License as published by @@ -21,6 +22,7 @@ # Authors: Olivier MATZ # Alan De Smet # Sergey Satskiy +# scito # # Inspired by diff2html.rb from Dave Burt # (mainly for html theme) @@ -33,32 +35,34 @@ # and display those directly. -import sys, re, htmlentitydefs, getopt, StringIO +import sys, re, htmlentitydefs, getopt, StringIO, codecs # minimum line size, we add a zero-sized breakable space every # LINESIZE characters linesize = 20 tabsize = 8 show_CR = False +encoding = "utf-8" -html_hdr = """ - +html_hdr = """ + + HTML Diff @@ -92,7 +96,7 @@ def sane(x): r = "" for i in x: j = ord(i) - if i not in ['\t', '\n'] and ((j < 32) or (j >= 127)): + if i not in ['\t', '\n'] and (j < 32): r = r + "." else: r = r + i @@ -100,9 +104,9 @@ def sane(x): def linediff(s, t): if len(s): - s = str(reduce(lambda x, y:x+y, [ sane(c) for c in s ])) + s = unicode(reduce(lambda x, y:x+y, [ sane(c) for c in s ])) if len(t): - t = str(reduce(lambda x, y:x+y, [ sane(c) for c in t ])) + t = unicode(reduce(lambda x, y:x+y, [ sane(c) for c in t ])) m, n = len(s), len(t) d = [[(0, 0) for i in range(n+1)] for i in range(m+1)] @@ -163,17 +167,17 @@ def linediff(s, t): def convert(s, linesize=0, ponct=0): i = 0 - t = "" + t = u"" for c in s: # used by diffs if c == DIFFON: - t += '' + t += u'' elif c == DIFFOFF: - t += "" + t += u"" # special html chars elif htmlentitydefs.codepoint2name.has_key(ord(c)): - t += "&%s;" % (htmlentitydefs.codepoint2name[ord(c)]) + t += u"&%s;" % (htmlentitydefs.codepoint2name[ord(c)]) i += 1 # special highlighted chars @@ -181,32 +185,34 @@ def convert(s, linesize=0, ponct=0): n = tabsize-(i%tabsize) if n == 0: n = tabsize - t += ('»'+' '*(n-1)) + t += (u'»'+' '*(n-1)) elif c == " " and ponct == 1: - t += '·' + t += u'·' elif c == "\n" and ponct == 1: if show_CR: - t += '\' + t += u'\' else: t += c i += 1 if linesize and (WORDBREAK.count(c) == 1): - t += '' + t += u'' i = 0 if linesize and i > linesize: i = 0 - t += "" + t += u"" return t def add_comment(s, output_file): - output_file.write('%s\n'%convert(s)) + output_file.write(('%s\n'%convert(s)).encode(encoding)) + def add_filename(f1, f2, output_file): - output_file.write("%s"%convert(f1, linesize=linesize)) - output_file.write("%s\n"%convert(f2, linesize=linesize)) + output_file.write(("%s"%convert(f1, linesize=linesize)).encode(encoding)) + output_file.write(("%s\n"%convert(f2, linesize=linesize)).encode(encoding)) + def add_hunk(output_file, show_hunk_infos): if show_hunk_infos: @@ -233,20 +239,20 @@ def add_line(s1, s2, output_file): type_name = "changed" s1, s2 = linediff(s1, s2) - output_file.write('' % type_name) + output_file.write(('' % type_name).encode(encoding)) if s1 != None and s1 != "": - output_file.write('%d ' % line1) - output_file.write('') - output_file.write(convert(s1, linesize=linesize, ponct=1)) + output_file.write(('%d ' % line1).encode(encoding)) + output_file.write(''.encode(encoding)) + output_file.write(convert(s1, linesize=linesize, ponct=1).encode(encoding)) output_file.write('') else: s1 = "" output_file.write(' ') if s2 != None and s2 != "": - output_file.write('%d '%line2) + output_file.write(('%d '%line2).encode(encoding)) output_file.write('') - output_file.write(convert(s2, linesize=linesize, ponct=1)) + output_file.write(convert(s2, linesize=linesize, ponct=1).encode(encoding)) output_file.write('') else: s2 = "" @@ -296,8 +302,8 @@ def parse_input(input_file, output_file, global hunk_off1, hunk_size1, hunk_off2, hunk_size2 if not exclude_headers: - output_file.write(html_hdr) - output_file.write(table_hdr) + output_file.write(html_hdr.format(encoding).encode(encoding)) + output_file.write(table_hdr.encode(encoding)) while True: l = input_file.readline() @@ -355,20 +361,22 @@ def parse_input(input_file, output_file, add_comment(l, output_file) empty_buffer(output_file) - output_file.write(table_footer) + output_file.write(table_footer.encode(encoding)) if not exclude_headers: - output_file.write(html_footer) + output_file.write(html_footer.encode(encoding)) def usage(): print ''' -diff2html.py [-i file] [-o file] [-x] +diff2html.py [-e encoding] [-i file] [-o file] [-x] diff2html.py -h Transform a unified diff from stdin to a colored side-by-side HTML page on stdout. +stdout may not work with UTF-8, instead use -o option. -i file set input file, else use stdin + -e encoding set file encoding (default utf-8) -o file set output file, else use stdout -x exclude html header and footer -t tabsize set tab size (default 8) @@ -381,6 +389,7 @@ page on stdout. def main(): global linesize, tabsize global show_CR + global encoding input_file = sys.stdin output_file = sys.stdout @@ -389,12 +398,12 @@ def main(): show_hunk_infos = False try: - opts, args = getopt.getopt(sys.argv[1:], "hi:o:xt:l:rk", - ["help", "input=", "output=", + opts, args = getopt.getopt(sys.argv[1:], "he:i:o:xt:l:rk", + ["help", "encoding=", "input=", "output=", "exclude-html-headers", "tabsize=", "linesize=", "show-cr", "show-hunk-infos"]) except getopt.GetoptError, err: - print str(err) # will print something like "option -a not recognized" + print unicode(err) # will print something like "option -a not recognized" usage() sys.exit(2) verbose = False @@ -402,10 +411,12 @@ def main(): if o in ("-h", "--help"): usage() sys.exit() + elif o in ("-e", "--encoding"): + encoding = a elif o in ("-i", "--input"): - input_file = open(a, "r") + input_file = codecs.open(a, "r", encoding) elif o in ("-o", "--output"): - output_file = open(a, "w") + output_file = codecs.open(a, "w") elif o in ("-x", "--exclude-html-headers"): exclude_headers = True elif o in ("-t", "--tabsize"):