X-Git-Url: http://git.droids-corp.org/?p=diff2html.git;a=blobdiff_plain;f=diff2html.py;h=92bbf362acf9a1b55b073c842181caa3112f2a59;hp=59d445dbf9cdf9dfd655a6bacf881feafd56c7bf;hb=c23d783c8f55be1471c90c51b9bbab4dd302e7c9;hpb=715a85a7ac2a121d30b421b128cb96533c3001b2
diff --git a/diff2html.py b/diff2html.py
index 59d445d..92bbf36 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
@@ -18,23 +19,14 @@
# Transform a unified diff from stdin to a colored
# side-by-side HTML page on stdout.
#
-# Author: Olivier MATZ
+# Authors: Olivier MATZ
+# Alan De Smet
+# Sergey Satskiy
+# scito
#
# Inspired by diff2html.rb from Dave Burt
# (mainly for html theme)
#
-# Changed by Alan De Smet 2009-01-25
-# - Remove headers and footers that are undesirable for for CVSTrac
-# integration.
-# - Change style sheet to own preferences
-# - Adjust LINESIZE code to reset counter and allow breaks whenever
-# WORDBREAK characters are encountered.
-# - Don't display offset info (it's redundant with the line numbers)
-# instead show vertical ellipsis
-# - If part of a "change" is actually blank, it's an addition or
-# deletion, not a "change" where the entire line changed.
-# - Don't display "\" for end of line; unnecessary noise.
-
# TODO:
# - The sane function currently mashes non-ASCII characters to "."
# Instead be clever and convert to something like "xF0"
@@ -43,58 +35,104 @@
# and display those directly.
-import sys, re, htmlentitydefs
+import sys, re, htmlentitydefs, getopt, StringIO, codecs, datetime
+
+# minimum line size, we add a zero-sized breakable space every
+# LINESIZE characters
+linesize = 20
+tabsize = 8
+show_CR = False
+encoding = "utf-8"
+lang = "en"
+
+desc = "File comparison"
+dtnow = datetime.datetime.now()
+modified_date = "%s+01:00"%dtnow.isoformat()
+
+html_hdr = """
+
+
+
+
+
+ HTML Diff{0}
+
+
+
+
+
+
+
+
+
+"""
+
+html_footer = """
+
+
+"""
-html_hdr="""
+table_hdr = """
"""
-html_footer="""
+table_footer = """
"""
-DIFFON="\x01"
-DIFFOFF="\x02"
+DIFFON = "\x01"
+DIFFOFF = "\x02"
-buffer=[]
-add_cpt, del_cpt = 0,0
-line1, line2 = 0,0
-hunk_off1, hunk_size1, hunk_off2, hunk_size2 = 0,0,0,0
+buf = []
+add_cpt, del_cpt = 0, 0
+line1, line2 = 0, 0
+hunk_off1, hunk_size1, hunk_off2, hunk_size2 = 0, 0, 0, 0
-# minimum line size, we add a zero-sized breakable space every
-# LINESIZE characters
-LINESIZE=20
-TAB=4
# Characters we're willing to word wrap on
-WORDBREAK=" \t;.,/):"
+WORDBREAK = " \t;.,/):"
def sane(x):
- r=""
+ r = ""
for i in x:
j = ord(i)
- if i not in ['\t', '\n'] and ((j < 32) or (j >= 127)):
- r=r+"."
+ if i not in ['\t', '\n'] and (j < 32):
+ r = r + "."
else:
- r=r+i
+ r = r + i
return r
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 ]))
-
- m,n = len(s), len(t)
- d=[[(0,0) for i in range(n+1)] for i in range(m+1)]
- x=[[(0,0) for i in range(n+1)] for i in range(m+1)]
-
-
- d[0][0] = (0, (0,0))
+ 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)]
+
+
+ d[0][0] = (0, (0, 0))
for i in range(m+1)[1:]:
- d[i][0] = (i,(i-1,0))
+ d[i][0] = (i,(i-1, 0))
for j in range(n+1)[1:]:
- d[0][j] = (j,(0,j-1))
+ d[0][j] = (j,(0, j-1))
for i in range(m+1)[1:]:
for j in range(n+1)[1:]:
@@ -102,34 +140,34 @@ def linediff(s, t):
cost = 0
else:
cost = 1
- d[i][j] = min((d[i-1][j][0] + 1, (i-1,j)),
- (d[i][j-1][0] + 1, (i,j-1)),
- (d[i-1][j-1][0] + cost, (i-1,j-1)))
-
- l=[]
- coord = (m,n)
- while coord != (0,0):
+ d[i][j] = min((d[i-1][j][0] + 1, (i-1, j)),
+ (d[i][j-1][0] + 1, (i, j-1)),
+ (d[i-1][j-1][0] + cost, (i-1, j-1)))
+
+ l = []
+ coord = (m, n)
+ while coord != (0, 0):
l.insert(0, coord)
- x,y = coord
+ x, y = coord
coord = d[x][y][1]
l1 = []
l2 = []
for coord in l:
- cx,cy = coord
+ cx, cy = coord
child_val = d[cx][cy][0]
-
+
father_coord = d[cx][cy][1]
- fx,fy = father_coord
+ fx, fy = father_coord
father_val = d[fx][fy][0]
diff = (cx-fx, cy-fy)
- if diff == (0,1):
+ if diff == (0, 1):
l1.append("")
l2.append(DIFFON + t[fy] + DIFFOFF)
- elif diff == (1,0):
+ elif diff == (1, 0):
l1.append(DIFFON + s[fx] + DIFFOFF)
l2.append("")
elif child_val-father_val == 1:
@@ -139,198 +177,296 @@ def linediff(s, t):
l1.append(s[fx])
l2.append(t[fy])
- r1,r2 = (reduce(lambda x,y:x+y, l1), reduce(lambda x,y:x+y, l2))
- return r1,r2
+ r1, r2 = (reduce(lambda x, y:x+y, l1), reduce(lambda x, y:x+y, l2))
+ return r1, r2
def convert(s, linesize=0, ponct=0):
- i=0
- t=""
- l=[]
+ i = 0
+ t = u""
for c in s:
# used by diffs
- if c==DIFFON:
- t += ''
- elif c==DIFFOFF:
- t += ""
+ if c == DIFFON:
+ t += u''
+ elif c == DIFFOFF:
+ 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
- elif c=="\t" and ponct==1:
- n = TAB-(i%TAB)
- if n==0:
- n=TAB
- t += ('»'+' '*(n-1))
- elif c==" " and ponct==1:
- t += '·'
- elif c=="\n" and ponct==1:
- 1 # Quietly drop it.
- #t += '\'
+ elif c == "\t" and ponct == 1:
+ n = tabsize-(i%tabsize)
+ if n == 0:
+ n = tabsize
+ t += (u'»'+' '*(n-1))
+ elif c == " " and ponct == 1:
+ t += u'·'
+ elif c == "\n" and ponct == 1:
+ if show_CR:
+ t += u'\'
else:
t += c
i += 1
- if linesize and (WORDBREAK.count(c)==1):
- t += ''
- i=0
- if linesize and i>linesize:
- i=0
- t += ""
-
+ if linesize and (WORDBREAK.count(c) == 1):
+ t += u''
+ i = 0
+ if linesize and i > linesize:
+ i = 0
+ t += u""
+
return t
-def add_comment(s):
- sys.stdout.write('
\n"%convert(f2, linesize=linesize)).encode(encoding))
-def add_hunk():
- global hunk_off1
- global hunk_size1
- global hunk_off2
- global hunk_size2
- # Don't bother displaying, it's redundant with the line numbers.
- #sys.stdout.write('
\n')
+ output_file.write('\n')
- if s1!="":
+ if s1 != "":
line1 += 1
- if s2!="":
+ if s2 != "":
line2 += 1
-def empty_buffer():
- global buffer
+def empty_buffer(output_file):
+ global buf
global add_cpt
global del_cpt
if del_cpt == 0 or add_cpt == 0:
- for l in buffer:
- add_line(l[0], l[1])
+ for l in buf:
+ add_line(l[0], l[1], output_file)
elif del_cpt != 0 and add_cpt != 0:
l0, l1 = [], []
- for l in buffer:
+ for l in buf:
if l[0] != None:
l0.append(l[0])
if l[1] != None:
l1.append(l[1])
- max = (len(l0) > len(l1)) and len(l0) or len(l1)
- for i in range(max):
+ max_len = (len(l0) > len(l1)) and len(l0) or len(l1)
+ for i in range(max_len):
s0, s1 = "", ""
- if i