D9600: Add scan-build python implementation

llvm-svn: 257533
diff --git a/clang/tools/scan-build-py/libscanbuild/report.py b/clang/tools/scan-build-py/libscanbuild/report.py
new file mode 100644
index 0000000..efc0a55
--- /dev/null
+++ b/clang/tools/scan-build-py/libscanbuild/report.py
@@ -0,0 +1,530 @@
+# -*- coding: utf-8 -*-
+#                     The LLVM Compiler Infrastructure
+#
+# This file is distributed under the University of Illinois Open Source
+# License. See LICENSE.TXT for details.
+""" This module is responsible to generate 'index.html' for the report.
+
+The input for this step is the output directory, where individual reports
+could be found. It parses those reports and generates 'index.html'. """
+
+import re
+import os
+import os.path
+import sys
+import shutil
+import time
+import tempfile
+import itertools
+import plistlib
+import glob
+import json
+import logging
+import contextlib
+from libscanbuild import duplicate_check
+from libscanbuild.clang import get_version
+
+__all__ = ['report_directory', 'document']
+
+
+@contextlib.contextmanager
+def report_directory(hint, keep):
+    """ Responsible for the report directory.
+
+    hint -- could specify the parent directory of the output directory.
+    keep -- a boolean value to keep or delete the empty report directory. """
+
+    stamp = time.strftime('scan-build-%Y-%m-%d-%H%M%S-', time.localtime())
+    name = tempfile.mkdtemp(prefix=stamp, dir=hint)
+
+    logging.info('Report directory created: %s', name)
+
+    try:
+        yield name
+    finally:
+        if os.listdir(name):
+            msg = "Run 'scan-view %s' to examine bug reports."
+            keep = True
+        else:
+            if keep:
+                msg = "Report directory '%s' contans no report, but kept."
+            else:
+                msg = "Removing directory '%s' because it contains no report."
+        logging.warning(msg, name)
+
+        if not keep:
+            os.rmdir(name)
+
+
+def document(args, output_dir, use_cdb):
+    """ Generates cover report and returns the number of bugs/crashes. """
+
+    html_reports_available = args.output_format in {'html', 'plist-html'}
+
+    logging.debug('count crashes and bugs')
+    crash_count = sum(1 for _ in read_crashes(output_dir))
+    bug_counter = create_counters()
+    for bug in read_bugs(output_dir, html_reports_available):
+        bug_counter(bug)
+    result = crash_count + bug_counter.total
+
+    if html_reports_available and result:
+        logging.debug('generate index.html file')
+        # common prefix for source files to have sort filenames
+        prefix = commonprefix_from(args.cdb) if use_cdb else os.getcwd()
+        # assemble the cover from multiple fragments
+        try:
+            fragments = []
+            if bug_counter.total:
+                fragments.append(bug_summary(output_dir, bug_counter))
+                fragments.append(bug_report(output_dir, prefix))
+            if crash_count:
+                fragments.append(crash_report(output_dir, prefix))
+            assemble_cover(output_dir, prefix, args, fragments)
+            # copy additinal files to the report
+            copy_resource_files(output_dir)
+            if use_cdb:
+                shutil.copy(args.cdb, output_dir)
+        finally:
+            for fragment in fragments:
+                os.remove(fragment)
+    return result
+
+
+def assemble_cover(output_dir, prefix, args, fragments):
+    """ Put together the fragments into a final report. """
+
+    import getpass
+    import socket
+    import datetime
+
+    if args.html_title is None:
+        args.html_title = os.path.basename(prefix) + ' - analyzer results'
+
+    with open(os.path.join(output_dir, 'index.html'), 'w') as handle:
+        indent = 0
+        handle.write(reindent("""
+        |<!DOCTYPE html>
+        |<html>
+        |  <head>
+        |    <title>{html_title}</title>
+        |    <link type="text/css" rel="stylesheet" href="scanview.css"/>
+        |    <script type='text/javascript' src="sorttable.js"></script>
+        |    <script type='text/javascript' src='selectable.js'></script>
+        |  </head>""", indent).format(html_title=args.html_title))
+        handle.write(comment('SUMMARYENDHEAD'))
+        handle.write(reindent("""
+        |  <body>
+        |    <h1>{html_title}</h1>
+        |    <table>
+        |      <tr><th>User:</th><td>{user_name}@{host_name}</td></tr>
+        |      <tr><th>Working Directory:</th><td>{current_dir}</td></tr>
+        |      <tr><th>Command Line:</th><td>{cmd_args}</td></tr>
+        |      <tr><th>Clang Version:</th><td>{clang_version}</td></tr>
+        |      <tr><th>Date:</th><td>{date}</td></tr>
+        |    </table>""", indent).format(html_title=args.html_title,
+                                         user_name=getpass.getuser(),
+                                         host_name=socket.gethostname(),
+                                         current_dir=prefix,
+                                         cmd_args=' '.join(sys.argv),
+                                         clang_version=get_version(args.clang),
+                                         date=datetime.datetime.today(
+                                         ).strftime('%c')))
+        for fragment in fragments:
+            # copy the content of fragments
+            with open(fragment, 'r') as input_handle:
+                shutil.copyfileobj(input_handle, handle)
+        handle.write(reindent("""
+        |  </body>
+        |</html>""", indent))
+
+
+def bug_summary(output_dir, bug_counter):
+    """ Bug summary is a HTML table to give a better overview of the bugs. """
+
+    name = os.path.join(output_dir, 'summary.html.fragment')
+    with open(name, 'w') as handle:
+        indent = 4
+        handle.write(reindent("""
+        |<h2>Bug Summary</h2>
+        |<table>
+        |  <thead>
+        |    <tr>
+        |      <td>Bug Type</td>
+        |      <td>Quantity</td>
+        |      <td class="sorttable_nosort">Display?</td>
+        |    </tr>
+        |  </thead>
+        |  <tbody>""", indent))
+        handle.write(reindent("""
+        |    <tr style="font-weight:bold">
+        |      <td class="SUMM_DESC">All Bugs</td>
+        |      <td class="Q">{0}</td>
+        |      <td>
+        |        <center>
+        |          <input checked type="checkbox" id="AllBugsCheck"
+        |                 onClick="CopyCheckedStateToCheckButtons(this);"/>
+        |        </center>
+        |      </td>
+        |    </tr>""", indent).format(bug_counter.total))
+        for category, types in bug_counter.categories.items():
+            handle.write(reindent("""
+        |    <tr>
+        |      <th>{0}</th><th colspan=2></th>
+        |    </tr>""", indent).format(category))
+            for bug_type in types.values():
+                handle.write(reindent("""
+        |    <tr>
+        |      <td class="SUMM_DESC">{bug_type}</td>
+        |      <td class="Q">{bug_count}</td>
+        |      <td>
+        |        <center>
+        |          <input checked type="checkbox"
+        |                 onClick="ToggleDisplay(this,'{bug_type_class}');"/>
+        |        </center>
+        |      </td>
+        |    </tr>""", indent).format(**bug_type))
+        handle.write(reindent("""
+        |  </tbody>
+        |</table>""", indent))
+        handle.write(comment('SUMMARYBUGEND'))
+    return name
+
+
+def bug_report(output_dir, prefix):
+    """ Creates a fragment from the analyzer reports. """
+
+    pretty = prettify_bug(prefix, output_dir)
+    bugs = (pretty(bug) for bug in read_bugs(output_dir, True))
+
+    name = os.path.join(output_dir, 'bugs.html.fragment')
+    with open(name, 'w') as handle:
+        indent = 4
+        handle.write(reindent("""
+        |<h2>Reports</h2>
+        |<table class="sortable" style="table-layout:automatic">
+        |  <thead>
+        |    <tr>
+        |      <td>Bug Group</td>
+        |      <td class="sorttable_sorted">
+        |        Bug Type
+        |        <span id="sorttable_sortfwdind">&nbsp;&#x25BE;</span>
+        |      </td>
+        |      <td>File</td>
+        |      <td>Function/Method</td>
+        |      <td class="Q">Line</td>
+        |      <td class="Q">Path Length</td>
+        |      <td class="sorttable_nosort"></td>
+        |    </tr>
+        |  </thead>
+        |  <tbody>""", indent))
+        handle.write(comment('REPORTBUGCOL'))
+        for current in bugs:
+            handle.write(reindent("""
+        |    <tr class="{bug_type_class}">
+        |      <td class="DESC">{bug_category}</td>
+        |      <td class="DESC">{bug_type}</td>
+        |      <td>{bug_file}</td>
+        |      <td class="DESC">{bug_function}</td>
+        |      <td class="Q">{bug_line}</td>
+        |      <td class="Q">{bug_path_length}</td>
+        |      <td><a href="{report_file}#EndPath">View Report</a></td>
+        |    </tr>""", indent).format(**current))
+            handle.write(comment('REPORTBUG', {'id': current['report_file']}))
+        handle.write(reindent("""
+        |  </tbody>
+        |</table>""", indent))
+        handle.write(comment('REPORTBUGEND'))
+    return name
+
+
+def crash_report(output_dir, prefix):
+    """ Creates a fragment from the compiler crashes. """
+
+    pretty = prettify_crash(prefix, output_dir)
+    crashes = (pretty(crash) for crash in read_crashes(output_dir))
+
+    name = os.path.join(output_dir, 'crashes.html.fragment')
+    with open(name, 'w') as handle:
+        indent = 4
+        handle.write(reindent("""
+        |<h2>Analyzer Failures</h2>
+        |<p>The analyzer had problems processing the following files:</p>
+        |<table>
+        |  <thead>
+        |    <tr>
+        |      <td>Problem</td>
+        |      <td>Source File</td>
+        |      <td>Preprocessed File</td>
+        |      <td>STDERR Output</td>
+        |    </tr>
+        |  </thead>
+        |  <tbody>""", indent))
+        for current in crashes:
+            handle.write(reindent("""
+        |    <tr>
+        |      <td>{problem}</td>
+        |      <td>{source}</td>
+        |      <td><a href="{file}">preprocessor output</a></td>
+        |      <td><a href="{stderr}">analyzer std err</a></td>
+        |    </tr>""", indent).format(**current))
+            handle.write(comment('REPORTPROBLEM', current))
+        handle.write(reindent("""
+        |  </tbody>
+        |</table>""", indent))
+        handle.write(comment('REPORTCRASHES'))
+    return name
+
+
+def read_crashes(output_dir):
+    """ Generate a unique sequence of crashes from given output directory. """
+
+    return (parse_crash(filename)
+            for filename in glob.iglob(os.path.join(output_dir, 'failures',
+                                                    '*.info.txt')))
+
+
+def read_bugs(output_dir, html):
+    """ Generate a unique sequence of bugs from given output directory.
+
+    Duplicates can be in a project if the same module was compiled multiple
+    times with different compiler options. These would be better to show in
+    the final report (cover) only once. """
+
+    parser = parse_bug_html if html else parse_bug_plist
+    pattern = '*.html' if html else '*.plist'
+
+    duplicate = duplicate_check(
+        lambda bug: '{bug_line}.{bug_path_length}:{bug_file}'.format(**bug))
+
+    bugs = itertools.chain.from_iterable(
+        # parser creates a bug generator not the bug itself
+        parser(filename)
+        for filename in glob.iglob(os.path.join(output_dir, pattern)))
+
+    return (bug for bug in bugs if not duplicate(bug))
+
+
+def parse_bug_plist(filename):
+    """ Returns the generator of bugs from a single .plist file. """
+
+    content = plistlib.readPlist(filename)
+    files = content.get('files')
+    for bug in content.get('diagnostics', []):
+        if len(files) <= int(bug['location']['file']):
+            logging.warning('Parsing bug from "%s" failed', filename)
+            continue
+
+        yield {
+            'result': filename,
+            'bug_type': bug['type'],
+            'bug_category': bug['category'],
+            'bug_line': int(bug['location']['line']),
+            'bug_path_length': int(bug['location']['col']),
+            'bug_file': files[int(bug['location']['file'])]
+        }
+
+
+def parse_bug_html(filename):
+    """ Parse out the bug information from HTML output. """
+
+    patterns = [re.compile(r'<!-- BUGTYPE (?P<bug_type>.*) -->$'),
+                re.compile(r'<!-- BUGFILE (?P<bug_file>.*) -->$'),
+                re.compile(r'<!-- BUGPATHLENGTH (?P<bug_path_length>.*) -->$'),
+                re.compile(r'<!-- BUGLINE (?P<bug_line>.*) -->$'),
+                re.compile(r'<!-- BUGCATEGORY (?P<bug_category>.*) -->$'),
+                re.compile(r'<!-- BUGDESC (?P<bug_description>.*) -->$'),
+                re.compile(r'<!-- FUNCTIONNAME (?P<bug_function>.*) -->$')]
+    endsign = re.compile(r'<!-- BUGMETAEND -->')
+
+    bug = {
+        'report_file': filename,
+        'bug_function': 'n/a',  # compatibility with < clang-3.5
+        'bug_category': 'Other',
+        'bug_line': 0,
+        'bug_path_length': 1
+    }
+
+    with open(filename) as handler:
+        for line in handler.readlines():
+            # do not read the file further
+            if endsign.match(line):
+                break
+            # search for the right lines
+            for regex in patterns:
+                match = regex.match(line.strip())
+                if match:
+                    bug.update(match.groupdict())
+                    break
+
+    encode_value(bug, 'bug_line', int)
+    encode_value(bug, 'bug_path_length', int)
+
+    yield bug
+
+
+def parse_crash(filename):
+    """ Parse out the crash information from the report file. """
+
+    match = re.match(r'(.*)\.info\.txt', filename)
+    name = match.group(1) if match else None
+    with open(filename) as handler:
+        lines = handler.readlines()
+        return {
+            'source': lines[0].rstrip(),
+            'problem': lines[1].rstrip(),
+            'file': name,
+            'info': name + '.info.txt',
+            'stderr': name + '.stderr.txt'
+        }
+
+
+def category_type_name(bug):
+    """ Create a new bug attribute from bug by category and type.
+
+    The result will be used as CSS class selector in the final report. """
+
+    def smash(key):
+        """ Make value ready to be HTML attribute value. """
+
+        return bug.get(key, '').lower().replace(' ', '_').replace("'", '')
+
+    return escape('bt_' + smash('bug_category') + '_' + smash('bug_type'))
+
+
+def create_counters():
+    """ Create counters for bug statistics.
+
+    Two entries are maintained: 'total' is an integer, represents the
+    number of bugs. The 'categories' is a two level categorisation of bug
+    counters. The first level is 'bug category' the second is 'bug type'.
+    Each entry in this classification is a dictionary of 'count', 'type'
+    and 'label'. """
+
+    def predicate(bug):
+        bug_category = bug['bug_category']
+        bug_type = bug['bug_type']
+        current_category = predicate.categories.get(bug_category, dict())
+        current_type = current_category.get(bug_type, {
+            'bug_type': bug_type,
+            'bug_type_class': category_type_name(bug),
+            'bug_count': 0
+        })
+        current_type.update({'bug_count': current_type['bug_count'] + 1})
+        current_category.update({bug_type: current_type})
+        predicate.categories.update({bug_category: current_category})
+        predicate.total += 1
+
+    predicate.total = 0
+    predicate.categories = dict()
+    return predicate
+
+
+def prettify_bug(prefix, output_dir):
+    def predicate(bug):
+        """ Make safe this values to embed into HTML. """
+
+        bug['bug_type_class'] = category_type_name(bug)
+
+        encode_value(bug, 'bug_file', lambda x: escape(chop(prefix, x)))
+        encode_value(bug, 'bug_category', escape)
+        encode_value(bug, 'bug_type', escape)
+        encode_value(bug, 'report_file', lambda x: escape(chop(output_dir, x)))
+        return bug
+
+    return predicate
+
+
+def prettify_crash(prefix, output_dir):
+    def predicate(crash):
+        """ Make safe this values to embed into HTML. """
+
+        encode_value(crash, 'source', lambda x: escape(chop(prefix, x)))
+        encode_value(crash, 'problem', escape)
+        encode_value(crash, 'file', lambda x: escape(chop(output_dir, x)))
+        encode_value(crash, 'info', lambda x: escape(chop(output_dir, x)))
+        encode_value(crash, 'stderr', lambda x: escape(chop(output_dir, x)))
+        return crash
+
+    return predicate
+
+
+def copy_resource_files(output_dir):
+    """ Copy the javascript and css files to the report directory. """
+
+    this_dir = os.path.dirname(os.path.realpath(__file__))
+    for resource in os.listdir(os.path.join(this_dir, 'resources')):
+        shutil.copy(os.path.join(this_dir, 'resources', resource), output_dir)
+
+
+def encode_value(container, key, encode):
+    """ Run 'encode' on 'container[key]' value and update it. """
+
+    if key in container:
+        value = encode(container[key])
+        container.update({key: value})
+
+
+def chop(prefix, filename):
+    """ Create 'filename' from '/prefix/filename' """
+
+    return filename if not len(prefix) else os.path.relpath(filename, prefix)
+
+
+def escape(text):
+    """ Paranoid HTML escape method. (Python version independent) """
+
+    escape_table = {
+        '&': '&amp;',
+        '"': '&quot;',
+        "'": '&apos;',
+        '>': '&gt;',
+        '<': '&lt;'
+    }
+    return ''.join(escape_table.get(c, c) for c in text)
+
+
+def reindent(text, indent):
+    """ Utility function to format html output and keep indentation. """
+
+    result = ''
+    for line in text.splitlines():
+        if len(line.strip()):
+            result += ' ' * indent + line.split('|')[1] + os.linesep
+    return result
+
+
+def comment(name, opts=dict()):
+    """ Utility function to format meta information as comment. """
+
+    attributes = ''
+    for key, value in opts.items():
+        attributes += ' {0}="{1}"'.format(key, value)
+
+    return '<!-- {0}{1} -->{2}'.format(name, attributes, os.linesep)
+
+
+def commonprefix_from(filename):
+    """ Create file prefix from a compilation database entries. """
+
+    with open(filename, 'r') as handle:
+        return commonprefix(item['file'] for item in json.load(handle))
+
+
+def commonprefix(files):
+    """ Fixed version of os.path.commonprefix. Return the longest path prefix
+    that is a prefix of all paths in filenames. """
+
+    result = None
+    for current in files:
+        if result is not None:
+            result = os.path.commonprefix([result, current])
+        else:
+            result = current
+
+    if result is None:
+        return ''
+    elif not os.path.isdir(result):
+        return os.path.dirname(result)
+    else:
+        return os.path.abspath(result)