view roundup/install_util.py @ 8180:d02ce1d14acd

feat: issue2551068 - Provide way to retrieve file/msg data via rest endpoint. Use Allow header to change format of /binary_content endpoint. If Allow header for endpoint is not application/json, it will be matched against the mime type for the file. */*, text/* are supported and will return the native mime type if present. Changes: move */* mime type from static dict of supported types. It was hardcoded to return json only. Now it can return a matching non-json mime type for the /binary_content endpoint. Edited some errors to explicitly add */* mime type. Cleanups to use ', ' separation in lists of valid mime types rather than just space separated. Remove ETag header when sending raw content. See issue 2551375 for background. Doc added to rest.txt. Small format fix up (add dash) in CHANGES.txt. Make passing an unset/None/False accept_mime_type to format_dispatch_output a 500 error. This used to be the fallback to produce a 406 error after all processing had happened. It should no longer be possible to take that code path as all 406 errors (with valid accept_mime_types) are generated before processing takes place. Make format_dispatch_output handle output other than json/xml so it can send back binary_content data. Removed a spurious client.response_code = 400 that seems to not be used. Tests added for all code paths. Database setup for tests msg and file entry. This required a file upload test to change so it doesn't look for file1 as the link returned by the upload. Download the link and verify the data rather than verifying the link. Multiple formatting changes to error messages to make all lists of valid mime types ', ' an not just space separated.
author John Rouillard <rouilj@ieee.org>
date Sun, 08 Dec 2024 17:22:33 -0500
parents 8e118eb20d86
children
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
import shutil
from hashlib import sha1

from roundup.anypy.strings import s2b

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(b"#SHA: "):
        # handle .py/.sh comment
        return lines[-1][6:].strip()
    elif lines[-1].startswith(b"<!-- SHA: "):
        # handle xml/html files
        fingerprint = lines[-1][10:]
        fingerprint = fingerprint.replace(b'-->', b'')
        return fingerprint.strip()
    elif lines[-1].startswith(b"/* SHA: "):
        # handle css files
        fingerprint = lines[-1][8:]
        fingerprint = fingerprint.replace(b'*/', b'')
        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, "rb")
    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 == s2b(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, "wb")

    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 = b'\n'.join(lines[:-1]) + b'\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(s2b("<!-- SHA: %s -->\n" %
                                (self.digest.hexdigest(),)))
        elif ext in hash_file_types:
            self.file.write(s2b("#SHA: %s\n" % (self.digest.hexdigest(),)))
        elif ext in slast_file_types:
            self.file.write(s2b("/* 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, 'rb')
        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], 'rb').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+b')
        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/