patchstream.py 17.2 KB
Newer Older
1 2
# Copyright (c) 2011 The Chromium OS Authors.
#
3
# SPDX-License-Identifier:	GPL-2.0+
4 5 6 7 8 9 10 11 12 13 14 15 16
#

import os
import re
import shutil
import tempfile

import command
import commit
import gitutil
from series import Series

# Tags that we detect and remove
17
re_remove = re.compile('^BUG=|^TEST=|^BRANCH=|^Change-Id:|^Review URL:'
18
    '|Reviewed-on:|Commit-\w*:')
19 20 21 22

# Lines which are allowed after a TEST= line
re_allowed_after_test = re.compile('^Signed-off-by:')

23
# Signoffs
24
re_signoff = re.compile('^Signed-off-by: *(.*)')
25

26 27 28
# The start of the cover letter
re_cover = re.compile('^Cover-letter:')

29 30 31
# A cover letter Cc
re_cover_cc = re.compile('^Cover-letter-cc: *(.*)')

32
# Patch series tag
33 34 35 36
re_series_tag = re.compile('^Series-([a-z-]*): *(.*)')

# Commit series tag
re_commit_tag = re.compile('^Commit-([a-z-]*): *(.*)')
37 38

# Commit tags that we want to collect and keep
39
re_tag = re.compile('^(Tested-by|Acked-by|Reviewed-by|Patch-cc): (.*)')
40 41

# The start of a new commit in the git log
42
re_commit = re.compile('^commit ([0-9a-f]*)$')
43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94

# We detect these since checkpatch doesn't always do it
re_space_before_tab = re.compile('^[+].* \t')

# States we can be in - can we use range() and still have comments?
STATE_MSG_HEADER = 0        # Still in the message header
STATE_PATCH_SUBJECT = 1     # In patch subject (first line of log for a commit)
STATE_PATCH_HEADER = 2      # In patch header (after the subject)
STATE_DIFFS = 3             # In the diff part (past --- line)

class PatchStream:
    """Class for detecting/injecting tags in a patch or series of patches

    We support processing the output of 'git log' to read out the tags we
    are interested in. We can also process a patch file in order to remove
    unwanted tags or inject additional ones. These correspond to the two
    phases of processing.
    """
    def __init__(self, series, name=None, is_log=False):
        self.skip_blank = False          # True to skip a single blank line
        self.found_test = False          # Found a TEST= line
        self.lines_after_test = 0        # MNumber of lines found after TEST=
        self.warn = []                   # List of warnings we have collected
        self.linenum = 1                 # Output line number we are up to
        self.in_section = None           # Name of start...END section we are in
        self.notes = []                  # Series notes
        self.section = []                # The current section...END section
        self.series = series             # Info about the patch series
        self.is_log = is_log             # True if indent like git log
        self.in_change = 0               # Non-zero if we are in a change list
        self.blank_count = 0             # Number of blank lines stored up
        self.state = STATE_MSG_HEADER    # What state are we in?
        self.signoff = []                # Contents of signoff line
        self.commit = None               # Current commit

    def AddToSeries(self, line, name, value):
        """Add a new Series-xxx tag.

        When a Series-xxx tag is detected, we come here to record it, if we
        are scanning a 'git log'.

        Args:
            line: Source line containing tag (useful for debug/error messages)
            name: Tag name (part after 'Series-')
            value: Tag value (part after 'Series-xxx: ')
        """
        if name == 'notes':
            self.in_section = name
            self.skip_blank = False
        if self.is_log:
            self.series.AddTag(self.commit, line, name, value)

95 96 97 98 99 100 101 102 103 104 105 106 107 108
    def AddToCommit(self, line, name, value):
        """Add a new Commit-xxx tag.

        When a Commit-xxx tag is detected, we come here to record it.

        Args:
            line: Source line containing tag (useful for debug/error messages)
            name: Tag name (part after 'Commit-')
            value: Tag value (part after 'Commit-xxx: ')
        """
        if name == 'notes':
            self.in_section = 'commit-' + name
            self.skip_blank = False

109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146
    def CloseCommit(self):
        """Save the current commit into our commit list, and reset our state"""
        if self.commit and self.is_log:
            self.series.AddCommit(self.commit)
            self.commit = None

    def ProcessLine(self, line):
        """Process a single line of a patch file or commit log

        This process a line and returns a list of lines to output. The list
        may be empty or may contain multiple output lines.

        This is where all the complicated logic is located. The class's
        state is used to move between different states and detect things
        properly.

        We can be in one of two modes:
            self.is_log == True: This is 'git log' mode, where most output is
                indented by 4 characters and we are scanning for tags

            self.is_log == False: This is 'patch' mode, where we already have
                all the tags, and are processing patches to remove junk we
                don't want, and add things we think are required.

        Args:
            line: text line to process

        Returns:
            list of output lines, or [] if nothing should be output
        """
        # Initially we have no output. Prepare the input line string
        out = []
        line = line.rstrip('\n')
        if self.is_log:
            if line[:4] == '    ':
                line = line[4:]

        # Handle state transition and skipping blank lines
147 148
        series_tag_match = re_series_tag.match(line)
        commit_tag_match = re_commit_tag.match(line)
149
        commit_match = re_commit.match(line) if self.is_log else None
150
        cover_cc_match = re_cover_cc.match(line)
151
        signoff_match = re_signoff.match(line)
152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175
        tag_match = None
        if self.state == STATE_PATCH_HEADER:
            tag_match = re_tag.match(line)
        is_blank = not line.strip()
        if is_blank:
            if (self.state == STATE_MSG_HEADER
                    or self.state == STATE_PATCH_SUBJECT):
                self.state += 1

            # We don't have a subject in the text stream of patch files
            # It has its own line with a Subject: tag
            if not self.is_log and self.state == STATE_PATCH_SUBJECT:
                self.state += 1
        elif commit_match:
            self.state = STATE_MSG_HEADER

        # If we are in a section, keep collecting lines until we see END
        if self.in_section:
            if line == 'END':
                if self.in_section == 'cover':
                    self.series.cover = self.section
                elif self.in_section == 'notes':
                    if self.is_log:
                        self.series.notes += self.section
176 177 178
                elif self.in_section == 'commit-notes':
                    if self.is_log:
                        self.commit.notes += self.section
179 180 181 182 183 184 185 186 187 188 189 190 191
                else:
                    self.warn.append("Unknown section '%s'" % self.in_section)
                self.in_section = None
                self.skip_blank = True
                self.section = []
            else:
                self.section.append(line)

        # Detect the commit subject
        elif not is_blank and self.state == STATE_PATCH_SUBJECT:
            self.commit.subject = line

        # Detect the tags we want to remove, and skip blank lines
192
        elif re_remove.match(line) and not commit_tag_match:
193 194 195 196 197 198 199 200 201 202 203 204 205 206
            self.skip_blank = True

            # TEST= should be the last thing in the commit, so remove
            # everything after it
            if line.startswith('TEST='):
                self.found_test = True
        elif self.skip_blank and is_blank:
            self.skip_blank = False

        # Detect the start of a cover letter section
        elif re_cover.match(line):
            self.in_section = 'cover'
            self.skip_blank = False

207 208 209 210
        elif cover_cc_match:
            value = cover_cc_match.group(1)
            self.AddToSeries(line, 'cover-cc', value)

211 212 213 214 215
        # If we are in a change list, key collected lines until a blank one
        elif self.in_change:
            if is_blank:
                # Blank line ends this change list
                self.in_change = 0
216
            elif line == '---':
217 218
                self.in_change = 0
                out = self.ProcessLine(line)
219
            else:
220 221
                if self.is_log:
                    self.series.AddChange(self.in_change, self.commit, line)
222 223 224
            self.skip_blank = False

        # Detect Series-xxx tags
225 226 227
        elif series_tag_match:
            name = series_tag_match.group(1)
            value = series_tag_match.group(2)
228 229 230 231 232 233 234 235 236 237 238 239
            if name == 'changes':
                # value is the version number: e.g. 1, or 2
                try:
                    value = int(value)
                except ValueError as str:
                    raise ValueError("%s: Cannot decode version info '%s'" %
                        (self.commit.hash, line))
                self.in_change = int(value)
            else:
                self.AddToSeries(line, name, value)
                self.skip_blank = True

240 241 242 243 244 245 246 247
        # Detect Commit-xxx tags
        elif commit_tag_match:
            name = commit_tag_match.group(1)
            value = commit_tag_match.group(2)
            if name == 'notes':
                self.AddToCommit(line, name, value)
                self.skip_blank = True

248 249 250
        # Detect the start of a new commit
        elif commit_match:
            self.CloseCommit()
251
            self.commit = commit.Commit(commit_match.group(1))
252 253 254 255

        # Detect tags in the commit message
        elif tag_match:
            # Remove Tested-by self, since few will take much notice
Ilya Yanok's avatar
Ilya Yanok committed
256
            if (tag_match.group(1) == 'Tested-by' and
257 258
                    tag_match.group(2).find(os.getenv('USER') + '@') != -1):
                self.warn.append("Ignoring %s" % line)
259
            elif tag_match.group(1) == 'Patch-cc':
260 261
                self.commit.AddCc(tag_match.group(2).split(','))
            else:
262
                out = [line]
263

264 265
        # Suppress duplicate signoffs
        elif signoff_match:
266
            if (self.is_log or not self.commit or
267
                self.commit.CheckDuplicateSignoff(signoff_match.group(1))):
268 269
                out = [line]

270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301
        # Well that means this is an ordinary line
        else:
            pos = 1
            # Look for ugly ASCII characters
            for ch in line:
                # TODO: Would be nicer to report source filename and line
                if ord(ch) > 0x80:
                    self.warn.append("Line %d/%d ('%s') has funny ascii char" %
                        (self.linenum, pos, line))
                pos += 1

            # Look for space before tab
            m = re_space_before_tab.match(line)
            if m:
                self.warn.append('Line %d/%d has space before tab' %
                    (self.linenum, m.start()))

            # OK, we have a valid non-blank line
            out = [line]
            self.linenum += 1
            self.skip_blank = False
            if self.state == STATE_DIFFS:
                pass

            # If this is the start of the diffs section, emit our tags and
            # change log
            elif line == '---':
                self.state = STATE_DIFFS

                # Output the tags (signeoff first), then change list
                out = []
                log = self.series.MakeChangeLog(self.commit)
302 303 304 305
                out += [line]
                if self.commit:
                    out += self.commit.notes
                out += [''] + log
306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355
            elif self.found_test:
                if not re_allowed_after_test.match(line):
                    self.lines_after_test += 1

        return out

    def Finalize(self):
        """Close out processing of this patch stream"""
        self.CloseCommit()
        if self.lines_after_test:
            self.warn.append('Found %d lines after TEST=' %
                    self.lines_after_test)

    def ProcessStream(self, infd, outfd):
        """Copy a stream from infd to outfd, filtering out unwanting things.

        This is used to process patch files one at a time.

        Args:
            infd: Input stream file object
            outfd: Output stream file object
        """
        # Extract the filename from each diff, for nice warnings
        fname = None
        last_fname = None
        re_fname = re.compile('diff --git a/(.*) b/.*')
        while True:
            line = infd.readline()
            if not line:
                break
            out = self.ProcessLine(line)

            # Try to detect blank lines at EOF
            for line in out:
                match = re_fname.match(line)
                if match:
                    last_fname = fname
                    fname = match.group(1)
                if line == '+':
                    self.blank_count += 1
                else:
                    if self.blank_count and (line == '-- ' or match):
                        self.warn.append("Found possible blank line(s) at "
                                "end of file '%s'" % last_fname)
                    outfd.write('+\n' * self.blank_count)
                    outfd.write(line + '\n')
                    self.blank_count = 0
        self.Finalize()


356
def GetMetaDataForList(commit_range, git_dir=None, count=None,
357
                       series = None, allow_overwrite=False):
358 359 360 361 362 363
    """Reads out patch series metadata from the commits

    This does a 'git log' on the relevant commits and pulls out the tags we
    are interested in.

    Args:
364 365 366 367 368
        commit_range: Range of commits to count (e.g. 'HEAD..base')
        git_dir: Path to git repositiory (None to use default)
        count: Number of commits to list, or None for no limit
        series: Series object to add information into. By default a new series
            is started.
369
        allow_overwrite: Allow tags to overwrite an existing tag
370 371
    Returns:
        A Series object containing information about the commits.
372
    """
373 374
    if not series:
        series = Series()
375
    series.allow_overwrite = allow_overwrite
376 377 378
    params = gitutil.LogCmd(commit_range,reverse=True, count=count,
                            git_dir=git_dir)
    stdout = command.RunPipe([params], capture=True).stdout
379 380 381 382 383 384
    ps = PatchStream(series, is_log=True)
    for line in stdout.splitlines():
        ps.ProcessLine(line)
    ps.Finalize()
    return series

385 386 387 388 389 390 391 392 393 394 395 396
def GetMetaData(start, count):
    """Reads out patch series metadata from the commits

    This does a 'git log' on the relevant commits and pulls out the tags we
    are interested in.

    Args:
        start: Commit to start from: 0=HEAD, 1=next one, etc.
        count: Number of commits to list
    """
    return GetMetaDataForList('HEAD~%d' % start, None, count)

397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483
def FixPatch(backup_dir, fname, series, commit):
    """Fix up a patch file, by adding/removing as required.

    We remove our tags from the patch file, insert changes lists, etc.
    The patch file is processed in place, and overwritten.

    A backup file is put into backup_dir (if not None).

    Args:
        fname: Filename to patch file to process
        series: Series information about this patch set
        commit: Commit object for this patch file
    Return:
        A list of errors, or [] if all ok.
    """
    handle, tmpname = tempfile.mkstemp()
    outfd = os.fdopen(handle, 'w')
    infd = open(fname, 'r')
    ps = PatchStream(series)
    ps.commit = commit
    ps.ProcessStream(infd, outfd)
    infd.close()
    outfd.close()

    # Create a backup file if required
    if backup_dir:
        shutil.copy(fname, os.path.join(backup_dir, os.path.basename(fname)))
    shutil.move(tmpname, fname)
    return ps.warn

def FixPatches(series, fnames):
    """Fix up a list of patches identified by filenames

    The patch files are processed in place, and overwritten.

    Args:
        series: The series object
        fnames: List of patch files to process
    """
    # Current workflow creates patches, so we shouldn't need a backup
    backup_dir = None  #tempfile.mkdtemp('clean-patch')
    count = 0
    for fname in fnames:
        commit = series.commits[count]
        commit.patch = fname
        result = FixPatch(backup_dir, fname, series, commit)
        if result:
            print '%d warnings for %s:' % (len(result), fname)
            for warn in result:
                print '\t', warn
            print
        count += 1
    print 'Cleaned %d patches' % count
    return series

def InsertCoverLetter(fname, series, count):
    """Inserts a cover letter with the required info into patch 0

    Args:
        fname: Input / output filename of the cover letter file
        series: Series object
        count: Number of patches in the series
    """
    fd = open(fname, 'r')
    lines = fd.readlines()
    fd.close()

    fd = open(fname, 'w')
    text = series.cover
    prefix = series.GetPatchPrefix()
    for line in lines:
        if line.startswith('Subject:'):
            # TODO: if more than 10 patches this should save 00/xx, not 0/xx
            line = 'Subject: [%s 0/%d] %s\n' % (prefix, count, text[0])

        # Insert our cover letter
        elif line.startswith('*** BLURB HERE ***'):
            # First the blurb test
            line = '\n'.join(text[1:]) + '\n'
            if series.get('notes'):
                line += '\n'.join(series.notes) + '\n'

            # Now the change list
            out = series.MakeChangeLog(None)
            line += '\n' + '\n'.join(out)
        fd.write(line)
    fd.close()