format_context_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("^\*{5,}$"),
    'OLD':    re.compile("^\*{3} [0-9]+"),
    'NEW':    re.compile("^\-{3} [0-9]+"),
}

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

codeChunkDict = {'OLD': [], 'NEW': []}

oldIndex = newIndex = -1



###----------------------------------------------------------------------
## 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 codeChunkDict['OLD'] or codeChunkDict['NEW']:
                print trHTMLCode % ('<br />\n'.join(codeChunkDict['OLD']), '<br />\n'.join(codeChunkDict['NEW']))

            codeChunkDict = {'OLD': [], 'NEW': []}

        else:

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

            if matchObj:

                newIndex, oldIndex = 0, int(line.split(' ')[1].split(',')[0])

            else:

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

                if matchObj:

                    oldIndex, newIndex = 0, int(line.split(' ')[1].split(',')[0])

                elif oldIndex:

                    codeChunkDict['OLD'].append(fn__applyStyle(line))

                elif newIndex:

                    codeChunkDict['NEW'].append(fn__applyStyle(line))



if codeChunkDict['OLD'] or codeChunkDict['NEW']:
    print trHTMLCode % ('<br />\n'.join(codeChunkDict['OLD']), '<br />\n'.join(codeChunkDict['NEW']))