#!/usr/bin/env python
#
# Copyright (C) 2004, 2005, 2006 Nathaniel Smith
# Copyright (C) 2007 Holger Hans Peter Freyther
#
# Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions
# are met:
#
# 1.  Redistributions of source code must retain the above copyright
#     notice, this list of conditions and the following disclaimer. 
# 2.  Redistributions in binary form must reproduce the above copyright
#     notice, this list of conditions and the following disclaimer in the
#     documentation and/or other materials provided with the distribution. 
# 3.  Neither the name of Apple Computer, Inc. ("Apple") nor the names of
#     its contributors may be used to endorse or promote products derived
#     from this software without specific prior written permission. 
#
# THIS SOFTWARE IS PROVIDED BY APPLE AND ITS CONTRIBUTORS "AS IS" AND ANY
# EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
# WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
# DISCLAIMED. IN NO EVENT SHALL APPLE OR ITS CONTRIBUTORS BE LIABLE FOR ANY
# DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
# (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
# LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
# ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
# (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
# THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

#
# HTML output inspired by the output of lcov as found on the GStreamer
# site. I assume this is not copyrightable.
#


#
# Read all CSV files and
#  Create an overview file
#
#


import sys
import csv
import glob
import time
import os
import os.path
import datetime
import shutil

os.environ["TTFPATH"] = ":".join(["/usr/share/fonts/truetype/" + d
                                  for d in "ttf-bitstream-vera",
                                           "freefont",
                                           "msttcorefonts"])
import matplotlib
matplotlib.use("Agg")
import matplotlib.pylab as m

level_LOW    = 10
level_MEDIUM = 70

def copy_files(dest_dir):
    """
    Copy the CSS and the png's to the destination directory
    """
    images = ["amber.png", "emerald.png", "glass.png", "ruby.png", "snow.png"]
    css    = "gcov.css"
    (base_path, name) = os.path.split(__file__)
    base_path = os.path.abspath(base_path)

    shutil.copyfile(os.path.join(base_path,css), os.path.join(dest_dir,css))
    map(lambda x: shutil.copyfile(os.path.join(base_path,x), os.path.join(dest_dir,x)), images)

def sumcov(cov):
        return "%.2f%% (%s/%s)" % (cov[1] * 100.0 / (cov[0] or 1), cov[1], cov[0])

def create_page(dest_dir, name):
    index = open(os.path.join(dest_dir, name), "w")
    index.write("""<HTML>
    <HEAD>
        <TITLE>WebKit test coverage information</TITLE>
        <link rel="stylesheet" type="text/css" href="gcov.css">
    </HEAD>
    <BODY>
    """)
    return index

def generate_header(file, last_time, total_lines, total_executed, path, image):
    product = "WebKit"
    date = time.strftime("%Y-%m-%d %H:%M:%S", time.gmtime(last_time))
    covered_lines = sumcov((total_lines, total_executed))

    file.write("""<table width="100%%" border=0 cellspacing=0 cellpadding=0>
    <tr><td class="title">GCOV code coverage report</td></tr>
    <tr><td class="ruler"><img src="glass.png" width=3 height=3 alt=""></td></tr>

    <tr>
      <td width="100%%">
        <table cellpadding=1 border=0 width="100%%">
        <tr>
          <td class="headerItem" width="20%%">Current&nbsp;view:</td>
          <td class="headerValue" width="80%%" colspan=4>%(path)s</td>
        </tr>
        <tr>
          <td class="headerItem" width="20%%">Test:</td>
          <td class="headerValue" width="80%%" colspan=4>%(product)s</td>
        </tr>
        <tr>
          <td class="headerItem" width="20%%">Date:</td>
          <td class="headerValue" width="20%%">%(date)s</td>
          <td width="20%%"></td>
          <td class="headerItem" width="20%%">Instrumented&nbsp;lines:</td>
          <td class="headerValue" width="20%%">%(total_lines)s</td>
        </tr>
        <tr>
          <td class="headerItem" width="20%%">Code&nbsp;covered:</td>
          <td class="headerValue" width="20%%">%(covered_lines)s</td>
          <td width="20%%"></td>
          <td class="headerItem" width="20%%">Executed&nbsp;lines:</td>
          <td class="headerValue" width="20%%">%(total_executed)s</td>
        </tr>
        </table>
      </td>
    </tr>
    <tr><td class="ruler"><img src="glass.png" width=3 height=3 alt=""></td></tr>
  </table>""" % vars())
    # disabled for now <tr><td><img src="%(image)s"></td></tr>

def generate_table_item(file, name, total_lines, covered_lines):
    covered_precise = (covered_lines*100.0)/(total_lines or 1.0)
    covered = int(round(covered_precise))
    remainder = 100-covered
    (image,perClass,numClass) = coverage_icon(covered_precise)
    site = "%s.html" % name.replace(os.path.sep,'__')
    file.write("""
        <tr>
      <td class="coverFile"><a href="%(site)s">%(name)s</a></td>
      <td class="coverBar" align="center">
        <table border=0 cellspacing=0 cellpadding=1><tr><td class="coverBarOutline"><img src="%(image)s" width=%(covered)s height=10 alt="%(covered_precise).2f"><img src="snow.png" width=%(remainder)s height=10 alt="%(covered_precise).2f"></td></tr></table>
      </td>
      <td class="%(perClass)s">%(covered_precise).2f&nbsp;%%</td>
      <td class="%(numClass)s">%(covered_lines)s&nbsp;/&nbsp;%(total_lines)s&nbsp;lines</td>
    </tr>
    """ % vars())

def generate_table_header_start(file):
  file.write("""<center>
  <table width="80%%" cellpadding=2 cellspacing=1 border=0>

    <tr>
      <td width="50%%"><br></td>
      <td width="15%%"></td>
      <td width="15%%"></td>
      <td width="20%%"></td>
    </tr>

    <tr>
      <td class="tableHead">Directory&nbsp;name</td>
      <td class="tableHead" colspan=3>Coverage</td>
    </tr>
    """)

def coverage_icon(percent):
    if percent < level_LOW:
        return ("ruby.png", "coverPerLo", "coverNumLo")
    elif percent < level_MEDIUM:
        return ("amber.png", "coverPerMed", "coverNumMed")
    else:
        return ("emerald.png", "coverPerHi", "coverNumHi")

def replace(text, *pairs):
    """
    From pydoc... almost identical at least
    """
    from string import split, join
    while pairs:
        (a,b) = pairs[0]
        text = join(split(text, a), b)
        pairs = pairs[1:]
    return text

def escape(text):
    """
    Escape string to be conform HTML
    """
    return replace(text,
                        ('&', '&amp;'),
                        ('<', '&lt;' ),
                        ('>', '&gt;' ) )

def generate_table_header_end(file):
    file.write("""</table>
    </center>""")

def write_title_page(dest_dir,plot_files, last_time, last_tot_lines, last_tot_covered, dir_series):
    """
    Write the index.html with a overview of each directory
    """
    index= create_page(dest_dir, "index.html")
    generate_header(index, last_time, last_tot_lines, last_tot_covered, "directory", "images/Total.png")
    # Create the directory overview
    generate_table_header_start(index)
    dirs = dir_series.keys()
    dirs.sort()
    for dir in dirs:
        (dir_files, total_lines, covered_lines,_) = dir_series[dir][-1]
        generate_table_item(index, dir, total_lines, covered_lines)
    generate_table_header_end(index)

    index.write("""</BODY></HTML>""")
    index.close()

def write_directory_site(dest_dir, plot_files, dir_name, last_time, dir_series, file_series):
    escaped_dir = dir_name.replace(os.path.sep,'__')
    site = create_page(dest_dir, "%s.html" % escaped_dir)
    (_,tot_lines,tot_covered,files) = dir_series[dir_name][-1]
    generate_header(site, last_time, tot_lines, tot_covered, "directory - %s" % dir_name, "images/%s.png" % escaped_dir)

    files.sort()

    generate_table_header_start(site)
    for file in files:
        (lines,covered) = file_series[file][-1]
        generate_table_item(site, file, lines, covered)

    generate_table_header_end(site)
    site.write("""</BODY></HTML>""")
    site.close()

def write_file_site(dest_dir, plot_files, file_name, last_time, data_dir, last_id, file_series):
    escaped_name = file_name.replace(os.path.sep,'__')
    site = create_page(dest_dir, "%s.html" % escaped_name)
    (tot_lines,tot_covered) = file_series[file_name][-1]
    generate_header(site, last_time, tot_lines, tot_covered, "file - %s" % file_name, "images/%s.png" % escaped_name)

    path = "%s/%s.annotated%s" % (data_dir,last_id,file_name)

    # In contrast to the lcov we want to show files that have been compiled
    # but have not been tested at all. This means we have sourcefiles with 0
    # lines covered in the path but they are not lcov files.
    # To identify them we check the first line now. If we see that we can
    # continue
    #         -:    0:Source:
    try:
        file = open(path, "r")
    except:
        return
    all_lines = file.read().split("\n")

    # Convert the gcov file to HTML if we have a chanche to do so
    # Scan each line and see if it was covered or not and escape the
    # text
    if len(all_lines) == 0 or not "-:    0:Source:" in all_lines[0]:
        site.write("<p>The file was not excercised</p>")
    else:
        site.write("""</br><table cellpadding=0 cellspacing=0 border=0>
    <tr>
      <td><br></td>
    </tr>
    <tr>
      <td><pre class="source">
    """)
        for line in all_lines:
            split_line = line.split(':',2)
            # e.g. at the EOF
            if len(split_line) == 1:
                continue
            line_number = split_line[1].strip()
            if line_number == "0":
                continue
            covered = 15*" "
            end = ""
            if "#####" in split_line[0]:
                covered = '<span class="lineNoCov">%15s' % "0"
                end = "</span>"
            elif split_line[0].strip() != "-":
                covered = '<span class="lineCov">%15s' % split_line[0].strip()
                end = "</span>"

            escaped_line = escape(split_line[2])
            str = '<span class="lineNum">%(line_number)10s </span>%(covered)s: %(escaped_line)s%(end)s\n' % vars()
            site.write(str)
        site.write("</pre></td></tr></table>")
    site.write("</BODY></HTML>")
    site.close()

def main(progname, args):
    if len(args) != 2:
        sys.exit("Usage: %s DATADIR OUTDIR" % progname)

    branch = "WebKit from trunk"
    datadir, outdir = args

    # First, load in all data from the data directory.
    data = []
    for datapath in glob.glob(os.path.join(datadir, "*.csv")):
        data.append(read_csv(datapath))
    # Sort by time
    data.sort()

    # Calculate time series for each file.
    times = [sample[0] for sample in data]
    times = [datetime.datetime.utcfromtimestamp(t) for t in times]
    times = m.date2num(times)
    all_files = {}
    all_dirs  = {}
    for sample in data:
        t, i, tot_line, tot_cover, per_file, per_dir = sample
        all_files.update(per_file)
        all_dirs.update(per_dir)
    total_series = []
    file_serieses = dict([[k, [(0, 0)] * len(times)] for k in all_files.keys()])
    dir_serieses  = dict([[k, [(0, 0, 0, [])] * len(times)] for k in all_dirs.keys()])
    data_idx = 0
    for sample in data:
        t, i, tot_line, tot_cover, per_file, per_dir = sample
        total_series.append([tot_line, tot_cover])
        for f, covinfo in per_file.items():
            file_serieses[f][data_idx] = covinfo
        for f, covinfo in per_dir.items():
            dir_serieses[f][data_idx] = covinfo
        data_idx += 1


    # Okay, ready to start outputting.  First make sure our directories
    # exist.
    if not os.path.exists(outdir):
        os.makedirs(outdir)
    rel_imgdir = "images"
    imgdir = os.path.join(outdir, rel_imgdir)
    if not os.path.exists(imgdir):
        os.makedirs(imgdir)

    # Now plot the actual graphs
    plot_files = {}
    #plot_files["Total"] = plot_coverage(times, total_series, imgdir, "Total")
    #for dir, series in dir_serieses.items():
    #    plot_files[dir] = plot_coverage(times, map(lambda (a,b,c,d):(b,c), series), imgdir, dir)
    #for f, series in file_serieses.items():
    #    plot_files[f] = plot_coverage(times, series, imgdir, f)

    # And look up the latest revision id, and coverage information
    last_time, last_id, last_tot_lines, last_tot_covered = data[-1][:4]

    # Now start generating our html file
    copy_files(outdir)
    write_title_page(outdir, plot_files, last_time, last_tot_lines, last_tot_covered, dir_serieses)

    dir_keys = dir_serieses.keys()
    dir_keys.sort()
    for dir_name in dir_keys:
        write_directory_site(outdir, plot_files, dir_name, last_time, dir_serieses, file_serieses)

    file_keys = file_serieses.keys()
    for file_name in file_keys:
        write_file_site(outdir, plot_files, file_name, last_time, datadir, last_id, file_serieses)

def read_csv(path):
    r = csv.reader(open(path, "r"))
    # First line is id, time
    for row in r:
        id, time_str = row
        break
    time = int(float(time_str))
    # Rest of lines are path, total_lines, covered_lines
    per_file = {}
    per_dir  = {}
    grand_total_lines, grand_covered_lines = 0, 0
    for row in r:
        path, total_lines_str, covered_lines_str = row
        total_lines = int(total_lines_str)
        covered_lines = int(covered_lines_str)
        grand_total_lines += total_lines
        grand_covered_lines += covered_lines
        per_file[path] = [total_lines, covered_lines]

        # Update dir statistics
        dirname = os.path.dirname(path)
        if not dirname in per_dir:
            per_dir[dirname] = (0,0,0,[])
        (dir_files,dir_total_lines,dir_covered_lines, files) = per_dir[dirname]
        dir_files += 1
        dir_total_lines += total_lines
        dir_covered_lines += covered_lines
        files.append(path)
        per_dir[dirname] = (dir_files,dir_total_lines,dir_covered_lines,files)
    return [time, id, grand_total_lines, grand_covered_lines, per_file, per_dir]


def plot_coverage(times, series, imgdir, name):
    percentages = [cov * 100.0 / (tot or 1) for tot, cov in series]
    m.plot_date(times, percentages, "b-")
    m.plot_date(times, percentages, "bo")
    m.title(name)
    m.ylim(0, 100)
    m.xlabel("Date")
    m.ylabel("Statement Coverage (%)")
    outfile_base = name.replace("/", "__") + ".png"
    outfile = os.path.join(imgdir, outfile_base)
    m.savefig(outfile, dpi=75)
    m.close()
    return outfile_base


if __name__ == "__main__":
    import sys
    main(sys.argv[0], sys.argv[1:])