diff2html.add_hunk() - Code Metrics - mmagnus/rna-tools - Measure and Improve Code Quality continuously with Scrutinizer

diff2html.add_hunk() A
last analyzed 2025-11-03 17:23 UTC

↳ Parent: diff2html

Complexity

Conditions

Size

Total Lines	7
Code Lines	5

Duplication

Lines	0
Ratio	0 %

Importance

Changes

Metric	Value
cc	2
eloc	5
nop	2
dl	0
loc	7
rs	10
c	0
b	0
f	0

#! /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
# the Free Software Foundation; either version 2 of the License, or
# (at your option) any later version.
#
# This program 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 this program; if not, write to the Free Software
# Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
#
#
# Transform a unified diff from stdin to a colored
# side-by-side HTML page on stdout.
#
# Authors: Olivier Matz <[email protected]>
#          Alan De Smet <[email protected]>
#          Sergey Satskiy <[email protected]>
#          scito <info at scito.ch>
#
# Inspired by diff2html.rb from Dave Burt <dave (at) burt.id.au>
# (mainly for html theme)
#
# TODO:
# - The sane function currently mashes non-ASCII characters to "."
#   Instead be clever and convert to something like "xF0"
#   (the hex value), and mark with a <span>.  Even more clever:
#   Detect if the character is "printable" for whatever definition,
#   and display those directly.

import sys, re, html.entities, getopt, io, codecs, datetime
from functools import reduce
try:
    from simplediff import diff, string_diff
except ImportError:
    sys.stderr.write("info: simplediff module not found, only linediff is available\n")
    sys.stderr.write("info: it can be downloaded at https://github.com/paulgb/simplediff\n")

# 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"
algorithm = 0

desc = "File comparison"
dtnow = datetime.datetime.now()
modified_date = "%s+01:00"%dtnow.isoformat()

html_hdr = """<!DOCTYPE html>
<html lang="{5}" dir="ltr"
    xmlns:dc="http://purl.org/dc/terms/">
<head>
    <meta charset="{1}" />
    <meta name="generator" content="diff2html.py (http://git.droids-corp.org/gitweb/?p=diff2html)" />
    <!--meta name="author" content="Fill in" /-->
    <title>HTML Diff{0}</title>
    <link rel="shortcut icon" href="data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAABAAAAAQAgMAAABinRfyAAAACVBMVEXAAAAAgAD///+K/HwIAAAAJUlEQVQI12NYBQQM2IgGBQ4mCIEQW7oyK4phampkGIQAc1G1AQCRxCNbyW92oQAAAABJRU5ErkJggg==" type="image/png" />
    <meta property="dc:language" content="{5}" />
    <!--meta property="dc:date" content="{3}" /-->
    <meta property="dc:modified" content="{4}" />
    <meta name="description" content="{2}" />
    <meta property="dc:abstract" content="{2}" />
    <style>
        table {{ border:0px; border-collapse:collapse; width: 100%; font-size:0.75em; font-family: Lucida Console, monospace }}
        td.line {{ color:#8080a0 }}
        th {{ background: black; color: white }}
        tr.diffunmodified td {{ background: #D0D0E0 }}
        tr.diffhunk td {{ background: #A0A0A0 }}
        tr.diffadded td {{ background: #CCFFCC }}
        tr.diffdeleted td {{ background: #FFCCCC }}
        tr.diffchanged td {{ background: #FFFFA0 }}
        span.diffchanged2 {{ background: #E0C880 }}
        span.diffponct {{ color: #B08080 }}
        tr.diffmisc td {{}}
        tr.diffseparator td {{}}
    </style>
</head>
<body>
"""

html_footer = """
<footer>
    <p>Modified at {1}. HTML formatting created by <a href="http://git.droids-corp.org/gitweb/?p=diff2html;a=summary">diff2html</a>.    </p>
</footer>
</body></html>
"""

table_hdr = """
		<table class="diff">
"""

table_footer = """
</table>
"""

DIFFON = "\x01"
DIFFOFF = "\x02"

buf = []
add_cpt, del_cpt = 0, 0
line1, line2 = 0, 0
hunk_off1, hunk_size1, hunk_off2, hunk_size2 = 0, 0, 0, 0


# Characters we're willing to word wrap on
WORDBREAK = " \t;.,/):-"

def sane(x):
    r = ""
    for i in x:
        j = ord(i)
        if i not in ['\t', '\n'] and (j < 32):
            r = r + "."
        else:
            r = r + i
    return r

def linediff(s, t):
    '''
    Original line diff algorithm of diff2html. It's character based.
    '''
    if len(s):
        s = str(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)]


    d[0][0] = (0, (0, 0))
    for i in range(m+1)[1:]:
        d[i][0] = (i,(i-1, 0))
    for j in range(n+1)[1:]:
        d[0][j] = (j,(0, j-1))

    for i in range(m+1)[1:]:
        for j in range(n+1)[1:]:
            if s[i-1] == t[j-1]:
                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):
        l.insert(0, coord)
        x, y = coord
        coord = d[x][y][1]

    l1 = []
    l2 = []

    for coord in l:
        cx, cy = coord
        child_val = d[cx][cy][0]

        father_coord = d[cx][cy][1]
        fx, fy = father_coord
        father_val = d[fx][fy][0]

        diff = (cx-fx, cy-fy)

        if diff == (0, 1):
            l1.append("")
            l2.append(DIFFON + t[fy] + DIFFOFF)
        elif diff == (1, 0):
            l1.append(DIFFON + s[fx] + DIFFOFF)
            l2.append("")
        elif child_val-father_val == 1:
            l1.append(DIFFON + s[fx] + DIFFOFF)
            l2.append(DIFFON + t[fy] + DIFFOFF)
        else:
            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


def diff_changed(old, new):
    '''
    Returns the differences basend on characters between two strings
    wrapped with DIFFON and DIFFOFF using `diff`.
    '''
    con = {'=': (lambda x: x),
           '+': (lambda x: DIFFON + x + DIFFOFF),
           '-': (lambda x: '')}
    return "".join([(con[a])("".join(b)) for a, b in diff(old, new)])


def diff_changed_ts(old, new):
    '''
    Returns a tuple for a two sided comparison based on characters, see `diff_changed`.
    '''
    return (diff_changed(new, old), diff_changed(old, new))


def word_diff(old, new):
    '''
    Returns the difference between the old and new strings based on words. Punctuation is not part of the word.

    Params:
        old the old string
        new the new string

    Returns:
        the output of `diff` on the two strings after splitting them
        on whitespace (a list of change instructions; see the docstring
        of `diff`)
    '''
    separator_pattern = '(\W+)';
    return diff(re.split(separator_pattern, old, flags=re.UNICODE), re.split(separator_pattern, new, flags=re.UNICODE))


def diff_changed_words(old, new):
    '''
    Returns the difference between two strings based on words (see `word_diff`)
    wrapped with DIFFON and DIFFOFF.

    Returns:
        the output of the diff expressed delimited with DIFFON and DIFFOFF.
    '''
    con = {'=': (lambda x: x),
           '+': (lambda x: DIFFON + x + DIFFOFF),
           '-': (lambda x: '')}
    return "".join([(con[a])("".join(b)) for a, b in word_diff(old, new)])


def diff_changed_words_ts(old, new):
    '''
    Returns a tuple for a two sided comparison based on words, see `diff_changed_words`.
    '''
    return (diff_changed_words(new, old), diff_changed_words(old, new))


def convert(s, linesize=0, ponct=0):
    i = 0
    t = ""
    for c in s:
        # used by diffs
        if c == DIFFON:
            t += '<span class="diffchanged2">'
        elif c == DIFFOFF:
            t += "</span>"

        # special html chars
        elif ord(c) in html.entities.codepoint2name:
            t += "&%s;" % (html.entities.codepoint2name[ord(c)])
            i += 1

        # special highlighted chars
        elif c == "\t" and ponct == 1:
            n = tabsize-(i%tabsize)
            if n == 0:
                n = tabsize
            t += ('<span class="diffponct">&raquo;</span>'+'&nbsp;'*(n-1))
        elif c == " " and ponct == 1:
            t += '<span class="diffponct">&middot;</span>'
        elif c == "\n" and ponct == 1:
            if show_CR:
                t += '<span class="diffponct">\</span>'
        else:
            t += c
            i += 1

        if linesize and (WORDBREAK.count(c) == 1):
            t += '&#8203;'
            i = 0
        if linesize and i > linesize:
            i = 0
            t += "&#8203;"

    return t


def add_comment(s, output_file):
    output_file.write(('<tr class="diffmisc"><td colspan="4">%s</td></tr>\n'%convert(s)).encode(encoding))


def add_filename(f1, f2, output_file):
    output_file.write(("<tr><th colspan='2'>%s</th>"%convert(f1, linesize=linesize)).encode(encoding))
    output_file.write(("<th colspan='2'>%s</th></tr>\n"%convert(f2, linesize=linesize)).encode(encoding))


def add_hunk(output_file, show_hunk_infos):
    if show_hunk_infos:
        output_file.write('<tr class="diffhunk"><td colspan="2">Offset %d, %d lines modified</td>'%(hunk_off1, hunk_size1))
        output_file.write('<td colspan="2">Offset %d, %d lines modified</td></tr>\n'%(hunk_off2, hunk_size2))
    else:
        # &#8942; - vertical ellipsis
        output_file.write('<tr class="diffhunk"><td colspan="2">&#8942;</td><td colspan="2">&#8942;</td></tr>')


def add_line(s1, s2, output_file):
    global line1
    global line2

    orig1 = s1
    orig2 = s2

    if s1 == None and s2 == None:
        type_name = "unmodified"
    elif s1 == None or s1 == "":
        type_name = "added"
    elif s2 == None or s1 == "":
        type_name = "deleted"
    elif s1 == s2:
        type_name = "unmodified"
    else:
        type_name = "changed"
        if algorithm == 1:
            s1, s2 = diff_changed_words_ts(orig1, orig2)
        elif algorithm == 2:
            s1, s2 = diff_changed_ts(orig1, orig2)
        else: # default
            s1, s2 = linediff(orig1, orig2)

    output_file.write(('<tr class="diff%s">' % type_name).encode(encoding))
    if s1 != None and s1 != "":
        output_file.write(('<td class="diffline">%d </td>' % line1).encode(encoding))
        output_file.write('<td class="diffpresent">'.encode(encoding))
        output_file.write(convert(s1, linesize=linesize, ponct=1).encode(encoding))
        output_file.write('</td>')
    else:
        s1 = ""
        output_file.write('<td colspan="2"> </td>')

    if s2 != None and s2 != "":
        output_file.write(('<td class="diffline">%d </td>'%line2).encode(encoding))
        output_file.write('<td class="diffpresent">')
        output_file.write(convert(s2, linesize=linesize, ponct=1).encode(encoding))
        output_file.write('</td>')
    else:
        s2 = ""
        output_file.write('<td colspan="2"></td>')

    output_file.write('</tr>\n')

    if s1 != "":
        line1 += 1
    if s2 != "":
        line2 += 1


def empty_buffer(output_file):
    global buf
    global add_cpt
    global del_cpt

    if del_cpt == 0 or add_cpt == 0:
        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 buf:
            if l[0] != None:
                l0.append(l[0])
            if l[1] != None:
                l1.append(l[1])
        max_len = (len(l0) > len(l1)) and len(l0) or len(l1)
        for i in range(max_len):
            s0, s1 = "", ""
            if i < len(l0):
                s0 = l0[i]
            if i < len(l1):
                s1 = l1[i]
            add_line(s0, s1, output_file)

    add_cpt, del_cpt = 0, 0
    buf = []


def parse_input(input_file, output_file, input_file_name, output_file_name,
                exclude_headers, show_hunk_infos):
    global add_cpt, del_cpt
    global line1, line2
    global hunk_off1, hunk_size1, hunk_off2, hunk_size2

    if not exclude_headers:
        title_suffix = ' ' + input_file_name
        output_file.write(html_hdr.format(title_suffix, encoding, desc, "", modified_date, lang).encode(encoding))
    output_file.write(table_hdr.encode(encoding))

    while True:
        l = input_file.readline()
        if l == "":
            break

        m = re.match('^--- ([^\s]*)', l)
        if m:
            empty_buffer(output_file)
            file1 = m.groups()[0]
            while True:
                l = input_file.readline()
                m = re.match('^\+\+\+ ([^\s]*)', l)
                if m:
                    file2 = m.groups()[0]
                    break
            add_filename(file1, file2, output_file)
            hunk_off1, hunk_size1, hunk_off2, hunk_size2 = 0, 0, 0, 0
            continue

        m = re.match("@@ -(\d+),?(\d*) \+(\d+),?(\d*)", l)
        if m:
            empty_buffer(output_file)
            hunk_data = [x=="" and 1 or int(x) for x in m.groups()]
            hunk_off1, hunk_size1, hunk_off2, hunk_size2 = hunk_data
            line1, line2 = hunk_off1, hunk_off2
            add_hunk(output_file, show_hunk_infos)
            continue

        if hunk_size1 == 0 and hunk_size2 == 0:
            empty_buffer(output_file)
            add_comment(l, output_file)
            continue

        if re.match("^\+", l):
            add_cpt += 1
            hunk_size2 -= 1
            buf.append((None, l[1:]))
            continue

        if re.match("^\-", l):
            del_cpt += 1
            hunk_size1 -= 1
            buf.append((l[1:], None))
            continue

        if re.match("^\ ", l) and hunk_size1 and hunk_size2:
            empty_buffer(output_file)
            hunk_size1 -= 1
            hunk_size2 -= 1
            buf.append((l[1:], l[1:]))
            continue

        empty_buffer(output_file)
        add_comment(l, output_file)

    empty_buffer(output_file)
    output_file.write(table_footer.encode(encoding))
    if not exclude_headers:
        output_file.write(html_footer.format("", dtnow.strftime("%d.%m.%Y")).encode(encoding))


def usage():
    print('''
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)
   -l linesize set maximum line size is there is no word break (default 20)
   -r          show \\r characters
   -k          show hunk infos
   -a algo     line diff algorithm (0: linediff characters, 1: word, 2: simplediff characters) (default 0)
   -h          show help and exit
''')

def main():
    global linesize, tabsize
    global show_CR
    global encoding
    global algorithm

    input_file_name = ''
    output_file_name = ''

    exclude_headers = False
    show_hunk_infos = False

    try:
        opts, args = getopt.getopt(sys.argv[1:], "he:i:o:xt:l:rka:",
                                   ["help", "encoding=", "input=", "output=",
                                    "exclude-html-headers", "tabsize=",
                                    "linesize=", "show-cr", "show-hunk-infos", "algorithm="])
    except getopt.GetoptError as err:
        print((str(err))) # will print something like "option -a not recognized"
        usage()
        sys.exit(2)
    verbose = False
    for o, a in opts:
        if o in ("-h", "--help"):
            usage()
            sys.exit()
        elif o in ("-e", "--encoding"):
            encoding = a
        elif o in ("-i", "--input"):
            input_file = codecs.open(a, "r", encoding)
            input_file_name = a
        elif o in ("-o", "--output"):
            output_file = codecs.open(a, "w")
            output_file_name = a
        elif o in ("-x", "--exclude-html-headers"):
            exclude_headers = True
        elif o in ("-t", "--tabsize"):
            tabsize = int(a)
        elif o in ("-l", "--linesize"):
            linesize = int(a)
        elif o in ("-r", "--show-cr"):
            show_CR = True
        elif o in ("-k", "--show-hunk-infos"):
            show_hunk_infos = True
        elif o in ("-a", "--algorithm"):
            algorithm = int(a)
        else:
            assert False, "unhandled option"

    # Use stdin if not input file is set
    if not ('input_file' in locals()):
        input_file = codecs.getreader(encoding)(sys.stdin)

    # Use stdout if not output file is set
    if not ('output_file' in locals()):
        output_file = codecs.getwriter(encoding)(sys.stdout)

    parse_input(input_file, output_file, input_file_name, output_file_name,
                exclude_headers, show_hunk_infos)

def parse_from_memory(txt, exclude_headers, show_hunk_infos):
    " Parses diff from memory and returns a string with html "
    input_stream = io.StringIO(txt)
    output_stream = io.StringIO()
    parse_input(input_stream, output_stream, '', '', exclude_headers, show_hunk_infos)
    return output_stream.getvalue()


if __name__ == "__main__":
    main()


1			#! /usr/bin/python
2			# coding=utf-8
3			#
4			# This program is free software; you can redistribute it and/or modify
5			# it under the terms of the GNU General Public License as published by
6			# the Free Software Foundation; either version 2 of the License, or
7			# (at your option) any later version.
8			#
9			# This program is distributed in the hope that it will be useful,
10			# but WITHOUT ANY WARRANTY; without even the implied warranty of
11			# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
12			# GNU General Public License for more details.
13			#
14			# You should have received a copy of the GNU General Public License
15			# along with this program; if not, write to the Free Software
16			# Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
17			#
18			#
19			# Transform a unified diff from stdin to a colored
20			# side-by-side HTML page on stdout.
21			#
22			# Authors: Olivier Matz <[email protected]>
23			# Alan De Smet <[email protected]>
24			# Sergey Satskiy <[email protected]>
25			# scito <info at scito.ch>
26			#
27			# Inspired by diff2html.rb from Dave Burt <dave (at) burt.id.au>
28			# (mainly for html theme)
29			#
30			# TODO:
31			# - The sane function currently mashes non-ASCII characters to "."
32			# Instead be clever and convert to something like "xF0"
33			# (the hex value), and mark with a <span>. Even more clever:
34			# Detect if the character is "printable" for whatever definition,
35			# and display those directly.
36
37			import sys, re, html.entities, getopt, io, codecs, datetime
38			from functools import reduce
39			try:
40			from simplediff import diff, string_diff
41			except ImportError:
42			sys.stderr.write("info: simplediff module not found, only linediff is available\n")
43			sys.stderr.write("info: it can be downloaded at https://github.com/paulgb/simplediff\n")
44
45			# minimum line size, we add a zero-sized breakable space every
46			# LINESIZE characters
47			linesize = 20
48			tabsize = 8
49			show_CR = False
50			encoding = "utf-8"
51			lang = "en"
52			algorithm = 0
53
54			desc = "File comparison"
55			dtnow = datetime.datetime.now()
56			modified_date = "%s+01:00"%dtnow.isoformat()
57
58			html_hdr = """<!DOCTYPE html>
59			<html lang="{5}" dir="ltr"
60			xmlns:dc="http://purl.org/dc/terms/">
61			<head>
62			<meta charset="{1}" />
63			<meta name="generator" content="diff2html.py (http://git.droids-corp.org/gitweb/?p=diff2html)" />
64			<!--meta name="author" content="Fill in" /-->
65			<title>HTML Diff{0}</title>
66			<link rel="shortcut icon" href="data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAABAAAAAQAgMAAABinRfyAAAACVBMVEXAAAAAgAD///+K/HwIAAAAJUlEQVQI12NYBQQM2IgGBQ4mCIEQW7oyK4phampkGIQAc1G1AQCRxCNbyW92oQAAAABJRU5ErkJggg==" type="image/png" />
67			<meta property="dc:language" content="{5}" />
68			<!--meta property="dc:date" content="{3}" /-->
69			<meta property="dc:modified" content="{4}" />
70			<meta name="description" content="{2}" />
71			<meta property="dc:abstract" content="{2}" />
72			<style>
73			table {{ border:0px; border-collapse:collapse; width: 100%; font-size:0.75em; font-family: Lucida Console, monospace }}
74			td.line {{ color:#8080a0 }}
75			th {{ background: black; color: white }}
76			tr.diffunmodified td {{ background: #D0D0E0 }}
77			tr.diffhunk td {{ background: #A0A0A0 }}
78			tr.diffadded td {{ background: #CCFFCC }}
79			tr.diffdeleted td {{ background: #FFCCCC }}
80			tr.diffchanged td {{ background: #FFFFA0 }}
81			span.diffchanged2 {{ background: #E0C880 }}
82			span.diffponct {{ color: #B08080 }}
83			tr.diffmisc td {{}}
84			tr.diffseparator td {{}}
85			</style>
86			</head>
87			<body>
88			"""
89
90			html_footer = """
91			<footer>
92			<p>Modified at {1}. HTML formatting created by <a href="http://git.droids-corp.org/gitweb/?p=diff2html;a=summary">diff2html</a>. </p>
93			</footer>
94			</body></html>
95			"""
96
97			table_hdr = """
98			<table class="diff">
99			"""
100
101			table_footer = """
102			</table>
103			"""
104
105			DIFFON = "\x01"
106			DIFFOFF = "\x02"
107
108			buf = []
109			add_cpt, del_cpt = 0, 0
110			line1, line2 = 0, 0
111			hunk_off1, hunk_size1, hunk_off2, hunk_size2 = 0, 0, 0, 0
112
113
114			# Characters we're willing to word wrap on
115			WORDBREAK = " \t;.,/):-"
116
117			def sane(x):
118			r = ""
119			for i in x:
120			j = ord(i)
121			if i not in ['\t', '\n'] and (j < 32):
122			r = r + "."
123			else:
124			r = r + i
125			return r
126
127			def linediff(s, t):
128			'''
129			Original line diff algorithm of diff2html. It's character based.
130			'''
131			if len(s):
132			s = str(reduce(lambda x, y:x+y, [ sane(c) for c in s ]))
133			if len(t):
134			t = str(reduce(lambda x, y:x+y, [ sane(c) for c in t ]))
135
136			m, n = len(s), len(t)
137			d = [[(0, 0) for i in range(n+1)] for i in range(m+1)]
138
139
140			d[0][0] = (0, (0, 0))
141			for i in range(m+1)[1:]:
142			d[i][0] = (i,(i-1, 0))
143			for j in range(n+1)[1:]:
144			d[0][j] = (j,(0, j-1))
145
146			for i in range(m+1)[1:]:
147			for j in range(n+1)[1:]:
148			if s[i-1] == t[j-1]:
149			cost = 0
150			else:
151			cost = 1
152			d[i][j] = min((d[i-1][j][0] + 1, (i-1, j)),
153			(d[i][j-1][0] + 1, (i, j-1)),
154			(d[i-1][j-1][0] + cost, (i-1, j-1)))
155
156			l = []
157			coord = (m, n)
158			while coord != (0, 0):
159			l.insert(0, coord)
160			x, y = coord
161			coord = d[x][y][1]
162
163			l1 = []
164			l2 = []
165
166			for coord in l:
167			cx, cy = coord
168			child_val = d[cx][cy][0]
169
170			father_coord = d[cx][cy][1]
171			fx, fy = father_coord
172			father_val = d[fx][fy][0]
173
174			diff = (cx-fx, cy-fy)
175
176			if diff == (0, 1):
177			l1.append("")
178			l2.append(DIFFON + t[fy] + DIFFOFF)
179			elif diff == (1, 0):
180			l1.append(DIFFON + s[fx] + DIFFOFF)
181			l2.append("")
182			elif child_val-father_val == 1:
183			l1.append(DIFFON + s[fx] + DIFFOFF)
184			l2.append(DIFFON + t[fy] + DIFFOFF)
185			else:
186			l1.append(s[fx])
187			l2.append(t[fy])
188
189			r1, r2 = (reduce(lambda x, y:x+y, l1), reduce(lambda x, y:x+y, l2))
190			return r1, r2
191
192
193			def diff_changed(old, new):
194			'''
195			Returns the differences basend on characters between two strings
196			wrapped with DIFFON and DIFFOFF using `diff`.
197			'''
198			con = {'=': (lambda x: x),
199			'+': (lambda x: DIFFON + x + DIFFOFF),
200			'-': (lambda x: '')}
201			return "".join([(con[a])("".join(b)) for a, b in diff(old, new)])
202
203
204			def diff_changed_ts(old, new):
205			'''
206			Returns a tuple for a two sided comparison based on characters, see `diff_changed`.
207			'''
208			return (diff_changed(new, old), diff_changed(old, new))
209
210
211			def word_diff(old, new):
212			'''
213			Returns the difference between the old and new strings based on words. Punctuation is not part of the word.
214
215			Params:
216			old the old string
217			new the new string
218
219			Returns:
220			the output of `diff` on the two strings after splitting them
221			on whitespace (a list of change instructions; see the docstring
222			of `diff`)
223			'''
224			separator_pattern = '(\W+)';
225			return diff(re.split(separator_pattern, old, flags=re.UNICODE), re.split(separator_pattern, new, flags=re.UNICODE))
226
227
228			def diff_changed_words(old, new):
229			'''
230			Returns the difference between two strings based on words (see `word_diff`)
231			wrapped with DIFFON and DIFFOFF.
232
233			Returns:
234			the output of the diff expressed delimited with DIFFON and DIFFOFF.
235			'''
236			con = {'=': (lambda x: x),
237			'+': (lambda x: DIFFON + x + DIFFOFF),
238			'-': (lambda x: '')}
239			return "".join([(con[a])("".join(b)) for a, b in word_diff(old, new)])
240
241
242			def diff_changed_words_ts(old, new):
243			'''
244			Returns a tuple for a two sided comparison based on words, see `diff_changed_words`.
245			'''
246			return (diff_changed_words(new, old), diff_changed_words(old, new))
247
248
249			def convert(s, linesize=0, ponct=0):
250			i = 0
251			t = ""
252			for c in s:
253			# used by diffs
254			if c == DIFFON:
255			t += '<span class="diffchanged2">'
256			elif c == DIFFOFF:
257			t += "</span>"
258
259			# special html chars
260			elif ord(c) in html.entities.codepoint2name:
261			t += "&%s;" % (html.entities.codepoint2name[ord(c)])
262			i += 1
263
264			# special highlighted chars
265			elif c == "\t" and ponct == 1:
266			n = tabsize-(i%tabsize)
267			if n == 0:
268			n = tabsize
269			t += ('<span class="diffponct">»</span>'+' '*(n-1))
270			elif c == " " and ponct == 1:
271			t += '<span class="diffponct">·</span>'
272			elif c == "\n" and ponct == 1:
273			if show_CR:
274			t += '<span class="diffponct">\</span>'
275			else:
276			t += c
277			i += 1
278
279			if linesize and (WORDBREAK.count(c) == 1):
280			t += ''
281			i = 0
282			if linesize and i > linesize:
283			i = 0
284			t += ""
285
286			return t
287
288
289			def add_comment(s, output_file):
290			output_file.write(('<tr class="diffmisc"><td colspan="4">%s</td></tr>\n'%convert(s)).encode(encoding))
291
292
293			def add_filename(f1, f2, output_file):
294			output_file.write(("<tr><th colspan='2'>%s</th>"%convert(f1, linesize=linesize)).encode(encoding))
295			output_file.write(("<th colspan='2'>%s</th></tr>\n"%convert(f2, linesize=linesize)).encode(encoding))
296
297
298			def add_hunk(output_file, show_hunk_infos):
299			if show_hunk_infos:
300			output_file.write('<tr class="diffhunk"><td colspan="2">Offset %d, %d lines modified</td>'%(hunk_off1, hunk_size1))
301			output_file.write('<td colspan="2">Offset %d, %d lines modified</td></tr>\n'%(hunk_off2, hunk_size2))
302			else:
303			# ⋮ - vertical ellipsis
304			output_file.write('<tr class="diffhunk"><td colspan="2">⋮</td><td colspan="2">⋮</td></tr>')
305
306
307			def add_line(s1, s2, output_file):
308			global line1
309			global line2
310
311			orig1 = s1
312			orig2 = s2
313
314			if s1 == None and s2 == None:
315			type_name = "unmodified"
316			elif s1 == None or s1 == "":
317			type_name = "added"
318			elif s2 == None or s1 == "":
319			type_name = "deleted"
320			elif s1 == s2:
321			type_name = "unmodified"
322			else:
323			type_name = "changed"
324			if algorithm == 1:
325			s1, s2 = diff_changed_words_ts(orig1, orig2)
326			elif algorithm == 2:
327			s1, s2 = diff_changed_ts(orig1, orig2)
328			else: # default
329			s1, s2 = linediff(orig1, orig2)
330
331			output_file.write(('<tr class="diff%s">' % type_name).encode(encoding))
332			if s1 != None and s1 != "":
333			output_file.write(('<td class="diffline">%d </td>' % line1).encode(encoding))
334			output_file.write('<td class="diffpresent">'.encode(encoding))
335			output_file.write(convert(s1, linesize=linesize, ponct=1).encode(encoding))
336			output_file.write('</td>')
337			else:
338			s1 = ""
339			output_file.write('<td colspan="2"> </td>')
340
341			if s2 != None and s2 != "":
342			output_file.write(('<td class="diffline">%d </td>'%line2).encode(encoding))
343			output_file.write('<td class="diffpresent">')
344			output_file.write(convert(s2, linesize=linesize, ponct=1).encode(encoding))
345			output_file.write('</td>')
346			else:
347			s2 = ""
348			output_file.write('<td colspan="2"></td>')
349
350			output_file.write('</tr>\n')
351
352			if s1 != "":
353			line1 += 1
354			if s2 != "":
355			line2 += 1
356
357
358			def empty_buffer(output_file):
359			global buf
360			global add_cpt
361			global del_cpt
362
363			if del_cpt == 0 or add_cpt == 0:
364			for l in buf:
365			add_line(l[0], l[1], output_file)
366
367			elif del_cpt != 0 and add_cpt != 0:
368			l0, l1 = [], []
369			for l in buf:
370			if l[0] != None:
371			l0.append(l[0])
372			if l[1] != None:
373			l1.append(l[1])
374			max_len = (len(l0) > len(l1)) and len(l0) or len(l1)
375			for i in range(max_len):
376			s0, s1 = "", ""
377			if i < len(l0):
378			s0 = l0[i]
379			if i < len(l1):
380			s1 = l1[i]
381			add_line(s0, s1, output_file)
382
383			add_cpt, del_cpt = 0, 0
384			buf = []
385
386
387			def parse_input(input_file, output_file, input_file_name, output_file_name,
388			exclude_headers, show_hunk_infos):
389			global add_cpt, del_cpt
390			global line1, line2
391			global hunk_off1, hunk_size1, hunk_off2, hunk_size2
392
393			if not exclude_headers:
394			title_suffix = ' ' + input_file_name
395			output_file.write(html_hdr.format(title_suffix, encoding, desc, "", modified_date, lang).encode(encoding))
396			output_file.write(table_hdr.encode(encoding))
397
398			while True:
399			l = input_file.readline()
400			if l == "":
401			break
402
403			m = re.match('^--- ([^\s]*)', l)
404			if m:
405			empty_buffer(output_file)
406			file1 = m.groups()[0]
407			while True:
408			l = input_file.readline()
409			m = re.match('^\+\+\+ ([^\s]*)', l)
410			if m:
411			file2 = m.groups()[0]
412			break
413			add_filename(file1, file2, output_file)
414			hunk_off1, hunk_size1, hunk_off2, hunk_size2 = 0, 0, 0, 0
415			continue
416
417			m = re.match("@@ -(\d+),?(\d) \+(\d+),?(\d)", l)
418			if m:
419			empty_buffer(output_file)
420			hunk_data = [x=="" and 1 or int(x) for x in m.groups()]
421			hunk_off1, hunk_size1, hunk_off2, hunk_size2 = hunk_data
422			line1, line2 = hunk_off1, hunk_off2
423			add_hunk(output_file, show_hunk_infos)
424			continue
425
426			if hunk_size1 == 0 and hunk_size2 == 0:
427			empty_buffer(output_file)
428			add_comment(l, output_file)
429			continue
430
431			if re.match("^\+", l):
432			add_cpt += 1
433			hunk_size2 -= 1
434			buf.append((None, l[1:]))
435			continue
436
437			if re.match("^\-", l):
438			del_cpt += 1
439			hunk_size1 -= 1
440			buf.append((l[1:], None))
441			continue
442
443			if re.match("^\ ", l) and hunk_size1 and hunk_size2:
444			empty_buffer(output_file)
445			hunk_size1 -= 1
446			hunk_size2 -= 1
447			buf.append((l[1:], l[1:]))
448			continue
449
450			empty_buffer(output_file)
451			add_comment(l, output_file)
452
453			empty_buffer(output_file)
454			output_file.write(table_footer.encode(encoding))
455			if not exclude_headers:
456			output_file.write(html_footer.format("", dtnow.strftime("%d.%m.%Y")).encode(encoding))
457
458
459			def usage():
460			print('''
461			diff2html.py [-e encoding] [-i file] [-o file] [-x]
462			diff2html.py -h
463
464			Transform a unified diff from stdin to a colored side-by-side HTML
465			page on stdout.
466			stdout may not work with UTF-8, instead use -o option.
467
468			-i file set input file, else use stdin
469			-e encoding set file encoding (default utf-8)
470			-o file set output file, else use stdout
471			-x exclude html header and footer
472			-t tabsize set tab size (default 8)
473			-l linesize set maximum line size is there is no word break (default 20)
474			-r show \\r characters
475			-k show hunk infos
476			-a algo line diff algorithm (0: linediff characters, 1: word, 2: simplediff characters) (default 0)
477			-h show help and exit
478			''')
479
480			def main():
481			global linesize, tabsize
482			global show_CR
483			global encoding
484			global algorithm
485
486			input_file_name = ''
487			output_file_name = ''
488
489			exclude_headers = False
490			show_hunk_infos = False
491
492			try:
493			opts, args = getopt.getopt(sys.argv[1:], "he:i:o:xt:l:rka:",
494			["help", "encoding=", "input=", "output=",
495			"exclude-html-headers", "tabsize=",
496			"linesize=", "show-cr", "show-hunk-infos", "algorithm="])
497			except getopt.GetoptError as err:
498			print((str(err))) # will print something like "option -a not recognized"
499			usage()
500			sys.exit(2)
501			verbose = False
502			for o, a in opts:
503			if o in ("-h", "--help"):
504			usage()
505			sys.exit()
506			elif o in ("-e", "--encoding"):
507			encoding = a
508			elif o in ("-i", "--input"):
509			input_file = codecs.open(a, "r", encoding)
510			input_file_name = a
511			elif o in ("-o", "--output"):
512			output_file = codecs.open(a, "w")
513			output_file_name = a
514			elif o in ("-x", "--exclude-html-headers"):
515			exclude_headers = True
516			elif o in ("-t", "--tabsize"):
517			tabsize = int(a)
518			elif o in ("-l", "--linesize"):
519			linesize = int(a)
520			elif o in ("-r", "--show-cr"):
521			show_CR = True
522			elif o in ("-k", "--show-hunk-infos"):
523			show_hunk_infos = True
524			elif o in ("-a", "--algorithm"):
525			algorithm = int(a)
526			else:
527			assert False, "unhandled option"
528
529			# Use stdin if not input file is set
530			if not ('input_file' in locals()):
531			input_file = codecs.getreader(encoding)(sys.stdin)
532
533			# Use stdout if not output file is set
534			if not ('output_file' in locals()):
535			output_file = codecs.getwriter(encoding)(sys.stdout)
536
537			parse_input(input_file, output_file, input_file_name, output_file_name,
538			exclude_headers, show_hunk_infos)
539
540			def parse_from_memory(txt, exclude_headers, show_hunk_infos):
541			" Parses diff from memory and returns a string with html "
542			input_stream = io.StringIO(txt)
543			output_stream = io.StringIO()
544			parse_input(input_stream, output_stream, '', '', exclude_headers, show_hunk_infos)
545			return output_stream.getvalue()
546
547
548			if __name__ == "__main__":
549			main()
550

mmagnus / rna-tools

diff2html.add_hunk() A last analyzed 2025-11-03 17:23 UTC

Complexity

Size

Duplication

Importance

Duplication Side-by-Side

Filter issues like

diff2html.add_hunk() A
last analyzed 2025-11-03 17:23 UTC