view roundup/install_util.py @ 5096:e74c3611b138

- issue2550636, issue2550909: Added support for Whoosh indexer. Also adds new config.ini setting called indexer to select indexer. See ``doc/upgrading.txt`` for details. Initial patch done by David Wolever. Patch modified (see ticket or below for changes), docs updated and committed. I have an outstanding issue with test/test_indexer.py. I have to comment out all imports and tests for indexers I don't have (i.e. mysql, postgres) otherwise no tests run. With that change made, dbm, sqlite (rdbms), xapian and whoosh indexes are all passing the indexer tests. Changes summary: 1) support native back ends dbm and rdbms. (original patch only fell through to dbm) 2) Developed whoosh stopfilter to not index stopwords or words outside the the maxlength and minlength limits defined in index_common.py. Required to pass the extremewords test_indexer test. Also I removed a call to .lower on the input text as the tokenizer I chose automatically does the lowercase. 3) Added support for max/min length to find. This was needed to pass extremewords test. 4) Added back a call to save_index in add_text. This allowed all but two tests to pass. 5) Fixed a call to: results = searcher.search(query.Term("identifier", identifier)) which had an extra parameter that is an error under current whoosh. 6) Set limit=None in search call for find() otherwise it only return 10 items. This allowed it to pass manyresults test Also due to changes in the roundup code removed the call in indexer_whoosh to from roundup.anypy.sets_ import set since we use the python builtin set.
author John Rouillard <rouilj@ieee.org>
date Sat, 25 Jun 2016 20:10:03 -0400
parents 9ba03348f923
children 88cf5614e0f4
line wrap: on
line source

#
# Copyright (c) 2001 Bizar Software Pty Ltd (http://www.bizarsoftware.com.au/)
# This module is free software, and you may redistribute it and/or modify
# under the same terms as Python, so long as this copyright message and
# disclaimer are retained in their original form.
#
# IN NO EVENT SHALL BIZAR SOFTWARE PTY LTD BE LIABLE TO ANY PARTY FOR
# DIRECT, INDIRECT, SPECIAL, INCIDENTAL, OR CONSEQUENTIAL DAMAGES ARISING
# OUT OF THE USE OF THIS CODE, EVEN IF THE AUTHOR HAS BEEN ADVISED OF THE
# POSSIBILITY OF SUCH DAMAGE.
#
# BIZAR SOFTWARE PTY LTD SPECIFICALLY DISCLAIMS ANY WARRANTIES, INCLUDING,
# BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
# FOR A PARTICULAR PURPOSE.  THE CODE PROVIDED HEREUNDER IS ON AN "AS IS"
# BASIS, AND THERE IS NO OBLIGATION WHATSOEVER TO PROVIDE MAINTENANCE,
# SUPPORT, UPDATES, ENHANCEMENTS, OR MODIFICATIONS.
# 

"""Support module to generate and check fingerprints of installed files.
"""
__docformat__ = 'restructuredtext'

import os, shutil
from hashlib import sha1

sgml_file_types = [".xml", ".ent", ".html"]
hash_file_types = [".py", ".sh", ".conf", ".cgi"]
slast_file_types = [".css"]

digested_file_types = sgml_file_types + hash_file_types + slast_file_types

def extractFingerprint(lines):
    # get fingerprint from last line
    if lines[-1].startswith("#SHA: "):
        # handle .py/.sh comment
        return lines[-1][6:].strip()
    elif lines[-1].startswith("<!-- SHA: "):
        # handle xml/html files
        fingerprint = lines[-1][10:]
        fingerprint = fingerprint.replace('-->', '')
        return fingerprint.strip()
    elif lines[-1].startswith("/* SHA: "):
        # handle css files
        fingerprint = lines[-1][8:]
        fingerprint = fingerprint.replace('*/', '')
        return fingerprint.strip()
    return None

def checkDigest(filename):
    """Read file, check for valid fingerprint, return TRUE if ok"""
    # open and read file
    inp = open(filename, "r")
    lines = inp.readlines()
    inp.close()

    fingerprint = extractFingerprint(lines)
    if fingerprint is None:
        return 0
    del lines[-1]

    # calculate current digest
    digest = sha1()
    for line in lines:
        digest.update(line)

    # compare current to stored digest
    return fingerprint == digest.hexdigest()


class DigestFile:
    """ A class that you can use like open() and that calculates
        and writes a SHA digest to the target file.
    """

    def __init__(self, filename):
        self.filename = filename
        self.digest = sha1()
        self.file = open(self.filename, "w")

    def write(self, data):
        lines = data.splitlines()
        # if the file is coming from an installed tracker being used as a
        # template, then we will want to re-calculate the SHA
        fingerprint = extractFingerprint(lines)
        if fingerprint is not None:
            data = '\n'.join(lines[:-1]) + '\n'
        self.file.write(data)
        self.digest.update(data)

    def close(self):
        file, ext = os.path.splitext(self.filename)

        if ext in sgml_file_types:
            self.file.write("<!-- SHA: %s -->\n" % (self.digest.hexdigest(),))
        elif ext in hash_file_types:
            self.file.write("#SHA: %s\n" % (self.digest.hexdigest(),))
        elif ext in slast_file_types:
            self.file.write("/* SHA: %s */\n" % (self.digest.hexdigest(),))

        self.file.close()


def copyDigestedFile(src, dst, copystat=1):
    """ Copy data from `src` to `dst`, adding a fingerprint to `dst`.
        If `copystat` is true, the file status is copied, too
        (like shutil.copy2).
    """
    if os.path.isdir(dst):
        dst = os.path.join(dst, os.path.basename(src))

    dummy, ext = os.path.splitext(src)
    if ext not in digested_file_types:
        if copystat:
            return shutil.copy2(src, dst)
        else:
            return shutil.copyfile(src, dst)

    fsrc = None
    fdst = None
    try:
        fsrc = open(src, 'r')
        fdst = DigestFile(dst)
        shutil.copyfileobj(fsrc, fdst)
    finally:
        if fdst: fdst.close()
        if fsrc: fsrc.close()

    if copystat: shutil.copystat(src, dst)


def test():
    import sys

    testdata = open(sys.argv[0], 'r').read()

    for ext in digested_file_types:
        testfile = "__digest_test" + ext

        out = DigestFile(testfile)
        out.write(testdata)
        out.close()

        assert checkDigest(testfile), "digest ok w/o modification"

        mod = open(testfile, 'r+')
        mod.seek(0)
        mod.write('# changed!')
        mod.close()

        assert not checkDigest(testfile), "digest fails after modification"

        os.remove(testfile)


if __name__ == '__main__':
    test()

# vim: set filetype=python ts=4 sw=4 et si

Roundup Issue Tracker: http://roundup-tracker.org/