format_unified_diff.py

import re, sys, string, os

###----------------------------------------------------------------------
## Define Function(s)
###----------------------------------------------------------------------

def fn__applyStyle(lineOfCode):

    indexZero = lineOfCode[0]

    lineOfCode = string.replace(lineOfCode[1:], ' ', ' ')
    lineOfCode = string.replace(string.replace(lineOfCode, '<', '&lt;'), '>', '&gt;')

    spanHTMLDict = {
      '+': "<span style='color: green'>%s</span>",
      '-': "<span style='color: red'>%s</span>",
      '!': "<span style='color: blue'>%s</span>",
      'x': "%s"
    }

    if indexZero not in ['+', '-', '!']:
        indexZero = 'x'

    return "    %s" % (spanHTMLDict[indexZero] % lineOfCode)



###----------------------------------------------------------------------
## Validate Script Argument(s)
###----------------------------------------------------------------------

if len(sys.argv) != 2:
    print 'Usage: %s <diff-output>' % sys.argv[0]
    sys.exit(1)

if not os.path.exists(sys.argv[1]):
    print 'Invalid Arguments: %s' % sys.argv[1]
    sys.exit(2)



###----------------------------------------------------------------------
## Define Global Variable(s)
###----------------------------------------------------------------------

inputFile = sys.argv[1]

regexDict = {
    'HEADER': re.compile("^@@ ([+-][0-9]+(,[0-9]+)? ?){1,2} @@$"),
    'ADD':    re.compile("^\+"),
    'DEL':    re.compile("^\-")
}

trHTMLCode = \
"""<tr>
  <td>
%s
  </td>
</tr>"""

codeChunkList = []


###----------------------------------------------------------------------
## Begin Program
###----------------------------------------------------------------------

with open(inputFile, 'r') as fileObj:

    ### Using Slice To Ignore First 2 Lines
    for line in fileObj.read().splitlines()[2:]:

        matchObj = re.match(regexDict['HEADER'], line)

        if matchObj:

            if codeChunkList:
                print trHTMLCode % '<br />\n'.join(codeChunkList)

            codeChunkList = []

        else:

            matchObj = re.match(regexDict['ADD'], line)

            if matchObj:

                codeChunkList.append(fn__applyStyle(line))

            else:

                matchObj = re.match(regexDict['DEL'], line)

                if matchObj:

                    codeChunkList.append(fn__applyStyle(line))

                else:

                    codeChunkList.append(fn__applyStyle(line))



if codeChunkList:
    print trHTMLCode % '<br />\n'.join(codeChunkList)