tests/test-revset.t

revset: add "matching" keyword

This keyword can be used to find revisions that "match" one or more fields of a
given set of revisions.

A revision matches another if all the selected fields (description, author,
branch, date, files, phase, parents, substate, user, summary and/or metadata)
match the corresponding values of those fields on the source revision.

By default this keyword looks for revisions that whose metadata match
(description, author and date) making it ideal to look for duplicate revisions.

matching takes 2 arguments (the second being optional):

1.- rev: a revset represeting a _single_ revision (e.g. tip, ., p1(.), etc)
2.- [field(s) to match]: an optional string containing the field or fields
(separated by spaces) to match.
    Valid fields are most regular context fields and some special fields:
    * regular fields:
      - description, author, branch, date, files, phase, parents,
      substate, user.
      Note that author and user are synonyms.
    * special fields: summary, metadata.
      - summary: matches the first line of the description.
      - metatadata: It is equivalent to matching 'description user date'
        (i.e. it matches the main metadata fields).

Examples:

1.- Look for revisions with the same metadata (author, description and date)
as the 11th revision:

hg log -r "matching(11)"

2.- Look for revisions with the same description as the 11th revision:

hg log -r "matching(11, description)"

3.- Look for revisions with the same 'summary' (i.e. same first line on their
description) as the 11th revision:

hg log -r "matching(11, summary)"

4.- Look for revisions with the same author as the current revision:

hg log -r "matching(., author)"

You could use 'user' rather than 'author' to get the same result.

5.- Look for revisions with the same description _AND_ author as the tip of the
repository:

hg log -r "matching(tip, 'author description')"

6.- Look for revisions touching the same files as the parent of the tip of the
repository

hg log -r "matching(p1(tip), files)"

7.- Look for revisions whose subrepos are on the same state as the tip of the
repository or its parent

hg log -r "matching(p1(tip):tip, substate)"

8.- Look for revisions whose author and subrepo states both match those of any
of the revisions on the stable branch:

hg log -r "matching(branch(stable), 'author substate')"

  $ "$TESTDIR/hghave" no-msys || exit 80 # MSYS will translate /a/b/c/ as if it was a real file path

  $ HGENCODING=utf-8
  $ export HGENCODING

  $ try() {
  >   hg debugrevspec --debug "$@"
  > }

  $ log() {
  >   hg log --template '{rev}\n' -r "$1"
  > }

  $ hg init repo
  $ cd repo

  $ echo a > a
  $ hg branch a
  marked working directory as branch a
  (branches are permanent and global, did you want a bookmark?)
  $ hg ci -Aqm0

  $ echo b > b
  $ hg branch b
  marked working directory as branch b
  (branches are permanent and global, did you want a bookmark?)
  $ hg ci -Aqm1

  $ rm a
  $ hg branch a-b-c-
  marked working directory as branch a-b-c-
  (branches are permanent and global, did you want a bookmark?)
  $ hg ci -Aqm2 -u Bob

  $ hg co 1
  1 files updated, 0 files merged, 0 files removed, 0 files unresolved
  $ hg branch +a+b+c+
  marked working directory as branch +a+b+c+
  (branches are permanent and global, did you want a bookmark?)
  $ hg ci -Aqm3

  $ hg co 2  # interleave
  0 files updated, 0 files merged, 1 files removed, 0 files unresolved
  $ echo bb > b
  $ hg branch -- -a-b-c-
  marked working directory as branch -a-b-c-
  (branches are permanent and global, did you want a bookmark?)
  $ hg ci -Aqm4 -d "May 12 2005"

  $ hg co 3
  2 files updated, 0 files merged, 0 files removed, 0 files unresolved
  $ hg branch /a/b/c/
  marked working directory as branch /a/b/c/
  (branches are permanent and global, did you want a bookmark?)
  $ hg ci -Aqm"5 bug"

  $ hg merge 4
  1 files updated, 0 files merged, 1 files removed, 0 files unresolved
  (branch merge, don't forget to commit)
  $ hg branch _a_b_c_
  marked working directory as branch _a_b_c_
  (branches are permanent and global, did you want a bookmark?)
  $ hg ci -Aqm"6 issue619"

  $ hg branch .a.b.c.
  marked working directory as branch .a.b.c.
  (branches are permanent and global, did you want a bookmark?)
  $ hg ci -Aqm7

  $ hg branch all
  marked working directory as branch all
  (branches are permanent and global, did you want a bookmark?)
  $ hg ci --close-branch -Aqm8
  abort: can only close branch heads
  [255]

  $ hg co 4
  0 files updated, 0 files merged, 0 files removed, 0 files unresolved
  $ hg branch é
  marked working directory as branch \xc3\xa9 (esc)
  (branches are permanent and global, did you want a bookmark?)
  $ hg ci -Aqm9

  $ hg tag -r6 1.0

  $ hg clone --quiet -U -r 7 . ../remote1
  $ hg clone --quiet -U -r 8 . ../remote2
  $ echo "[paths]" >> .hg/hgrc
  $ echo "default = ../remote1" >> .hg/hgrc

names that should work without quoting

  $ try a
  ('symbol', 'a')
  0
  $ try b-a
  (minus
    ('symbol', 'b')
    ('symbol', 'a'))
  1
  $ try _a_b_c_
  ('symbol', '_a_b_c_')
  6
  $ try _a_b_c_-a
  (minus
    ('symbol', '_a_b_c_')
    ('symbol', 'a'))
  6
  $ try .a.b.c.
  ('symbol', '.a.b.c.')
  7
  $ try .a.b.c.-a
  (minus
    ('symbol', '.a.b.c.')
    ('symbol', 'a'))
  7
  $ try -- '-a-b-c-' # complains
  hg: parse error at 7: not a prefix: end
  [255]
  $ log -a-b-c- # succeeds with fallback
  4
  $ try -- -a-b-c--a # complains
  (minus
    (minus
      (minus
        (negate
          ('symbol', 'a'))
        ('symbol', 'b'))
      ('symbol', 'c'))
    (negate
      ('symbol', 'a')))
  abort: unknown revision '-a'!
  [255]
  $ try é
  ('symbol', '\xc3\xa9')
  9

quoting needed

  $ try '"-a-b-c-"-a'
  (minus
    ('string', '-a-b-c-')
    ('symbol', 'a'))
  4

  $ log '1 or 2'
  1
  2
  $ log '1|2'
  1
  2
  $ log '1 and 2'
  $ log '1&2'
  $ try '1&2|3' # precedence - and is higher
  (or
    (and
      ('symbol', '1')
      ('symbol', '2'))
    ('symbol', '3'))
  3
  $ try '1|2&3'
  (or
    ('symbol', '1')
    (and
      ('symbol', '2')
      ('symbol', '3')))
  1
  $ try '1&2&3' # associativity
  (and
    (and
      ('symbol', '1')
      ('symbol', '2'))
    ('symbol', '3'))
  $ try '1|(2|3)'
  (or
    ('symbol', '1')
    (group
      (or
        ('symbol', '2')
        ('symbol', '3'))))
  1
  2
  3
  $ log '1.0' # tag
  6
  $ log 'a' # branch
  0
  $ log '2785f51ee'
  0
  $ log 'date(2005)'
  4
  $ log 'date(this is a test)'
  hg: parse error at 10: unexpected token: symbol
  [255]
  $ log 'date()'
  hg: parse error: date requires a string
  [255]
  $ log 'date'
  hg: parse error: can't use date here
  [255]
  $ log 'date('
  hg: parse error at 5: not a prefix: end
  [255]
  $ log 'date(tip)'
  abort: invalid date: 'tip'
  [255]
  $ log '"date"'
  abort: unknown revision 'date'!
  [255]
  $ log 'date(2005) and 1::'
  4

  $ log 'ancestor(1)'
  hg: parse error: ancestor requires two arguments
  [255]
  $ log 'ancestor(4,5)'
  1
  $ log 'ancestor(4,5) and 4'
  $ log 'ancestors(5)'
  0
  1
  3
  5
  $ log 'author(bob)'
  2
  $ log 'branch(é)'
  8
  9
  $ log 'children(ancestor(4,5))'
  2
  3
  $ log 'closed()'
  $ log 'contains(a)'
  0
  1
  3
  5
  $ log 'desc(B)'
  5
  $ log 'descendants(2 or 3)'
  2
  3
  4
  5
  6
  7
  8
  9
  $ log 'file(b)'
  1
  4
  $ log 'follow()'
  0
  1
  2
  4
  8
  9
  $ log 'grep("issue\d+")'
  6
  $ try 'grep("(")' # invalid regular expression
  (func
    ('symbol', 'grep')
    ('string', '('))
  hg: parse error: invalid match pattern: unbalanced parenthesis
  [255]
  $ try 'grep("\bissue\d+")'
  (func
    ('symbol', 'grep')
    ('string', '\x08issue\\d+'))
  $ try 'grep(r"\bissue\d+")'
  (func
    ('symbol', 'grep')
    ('string', '\\bissue\\d+'))
  6
  $ try 'grep(r"\")'
  hg: parse error at 7: unterminated string
  [255]
  $ log 'head()'
  0
  1
  2
  3
  4
  5
  6
  7
  9
  $ log 'heads(6::)'
  7
  $ log 'keyword(issue)'
  6
  $ log 'limit(head(), 1)'
  0
  $ log 'max(contains(a))'
  5
  $ log 'min(contains(a))'
  0
  $ log 'merge()'
  6
  $ log 'modifies(b)'
  4
  $ log 'id(5)'
  2
  $ log 'outgoing()'
  8
  9
  $ log 'outgoing("../remote1")'
  8
  9
  $ log 'outgoing("../remote2")'
  3
  5
  6
  7
  9
  $ log 'p1(merge())'
  5
  $ log 'p2(merge())'
  4
  $ log 'parents(merge())'
  4
  5
  $ log 'removes(a)'
  2
  6
  $ log 'roots(all())'
  0
  $ log 'reverse(2 or 3 or 4 or 5)'
  5
  4
  3
  2
  $ log 'rev(5)'
  5
  $ log 'sort(limit(reverse(all()), 3))'
  7
  8
  9
  $ log 'sort(2 or 3 or 4 or 5, date)'
  2
  3
  5
  4
  $ log 'tagged()'
  6
  $ log 'tag()'
  6
  $ log 'tag(1.0)'
  6
  $ log 'tag(tip)'
  9
  $ log 'tag(unknown)'
  abort: tag 'unknown' does not exist
  [255]
  $ log 'branch(unknown)'
  abort: unknown revision 'unknown'!
  [255]
  $ log 'user(bob)'
  2

  $ log '4::8'
  4
  8
  $ log '4:8'
  4
  5
  6
  7
  8

  $ log 'sort(!merge() & (modifies(b) | user(bob) | keyword(bug) | keyword(issue) & 1::9), "-date")'
  4
  2
  5

  $ log 'not 0 and 0:2'
  1
  2
  $ log 'not 1 and 0:2'
  0
  2
  $ log 'not 2 and 0:2'
  0
  1
  $ log '(1 and 2)::'
  $ log '(1 and 2):'
  $ log '(1 and 2):3'
  $ log 'sort(head(), -rev)'
  9
  7
  6
  5
  4
  3
  2
  1
  0
  $ log '4::8 - 8'
  4

issue2437

  $ log '3 and p1(5)'
  3
  $ log '4 and p2(6)'
  4
  $ log '1 and parents(:2)'
  1
  $ log '2 and children(1:)'
  2
  $ log 'roots(all()) or roots(all())'
  0
  $ log 'heads(branch(é)) or heads(branch(é))'
  9
  $ log 'ancestors(8) and (heads(branch("-a-b-c-")) or heads(branch(é)))'
  4

issue2654: report a parse error if the revset was not completely parsed

  $ log '1 OR 2'
  hg: parse error at 2: invalid token
  [255]

or operator should preserve ordering:
  $ log 'reverse(2::4) or tip'
  4
  2
  9

parentrevspec

  $ log 'merge()^0'
  6
  $ log 'merge()^'
  5
  $ log 'merge()^1'
  5
  $ log 'merge()^2'
  4
  $ log 'merge()^^'
  3
  $ log 'merge()^1^'
  3
  $ log 'merge()^^^'
  1

  $ log 'merge()~0'
  6
  $ log 'merge()~1'
  5
  $ log 'merge()~2'
  3
  $ log 'merge()~2^1'
  1
  $ log 'merge()~3'
  1

  $ log '(-3:tip)^'
  4
  6
  8

  $ log 'tip^foo'
  hg: parse error: ^ expects a number 0, 1, or 2
  [255]

aliases:

  $ echo '[revsetalias]' >> .hg/hgrc
  $ echo 'm = merge()' >> .hg/hgrc
  $ echo 'sincem = descendants(m)' >> .hg/hgrc
  $ echo 'd($1) = reverse(sort($1, date))' >> .hg/hgrc
  $ echo 'rs(ARG1, ARG2) = reverse(sort(ARG1, ARG2))' >> .hg/hgrc
  $ echo 'rs4(ARG1, ARGA, ARGB, ARG2) = reverse(sort(ARG1, ARG2))' >> .hg/hgrc

  $ try m
  ('symbol', 'm')
  (func
    ('symbol', 'merge')
    None)
  6

test alias recursion

  $ try sincem
  ('symbol', 'sincem')
  (func
    ('symbol', 'descendants')
    (func
      ('symbol', 'merge')
      None))
  6
  7

test infinite recursion

  $ echo 'recurse1 = recurse2' >> .hg/hgrc
  $ echo 'recurse2 = recurse1' >> .hg/hgrc
  $ try recurse1
  ('symbol', 'recurse1')
  hg: parse error: infinite expansion of revset alias "recurse1" detected
  [255]

test nesting and variable passing

  $ echo 'nested($1) = nested2($1)' >> .hg/hgrc
  $ echo 'nested2($1) = nested3($1)' >> .hg/hgrc
  $ echo 'nested3($1) = max($1)' >> .hg/hgrc
  $ try 'nested(2:5)'
  (func
    ('symbol', 'nested')
    (range
      ('symbol', '2')
      ('symbol', '5')))
  (func
    ('symbol', 'max')
    (range
      ('symbol', '2')
      ('symbol', '5')))
  5

test variable isolation, variable placeholders are rewritten as string
then parsed and matched again as string. Check they do not leak too
far away.

  $ echo 'injectparamasstring = max("$1")' >> .hg/hgrc
  $ echo 'callinjection($1) = descendants(injectparamasstring)' >> .hg/hgrc
  $ try 'callinjection(2:5)'
  (func
    ('symbol', 'callinjection')
    (range
      ('symbol', '2')
      ('symbol', '5')))
  (func
    ('symbol', 'descendants')
    (func
      ('symbol', 'max')
      ('string', '$1')))
  abort: unknown revision '$1'!
  [255]

  $ try 'd(2:5)'
  (func
    ('symbol', 'd')
    (range
      ('symbol', '2')
      ('symbol', '5')))
  (func
    ('symbol', 'reverse')
    (func
      ('symbol', 'sort')
      (list
        (range
          ('symbol', '2')
          ('symbol', '5'))
        ('symbol', 'date'))))
  4
  5
  3
  2
  $ try 'rs(2 or 3, date)'
  (func
    ('symbol', 'rs')
    (list
      (or
        ('symbol', '2')
        ('symbol', '3'))
      ('symbol', 'date')))
  (func
    ('symbol', 'reverse')
    (func
      ('symbol', 'sort')
      (list
        (or
          ('symbol', '2')
          ('symbol', '3'))
        ('symbol', 'date'))))
  3
  2
  $ try 'rs()'
  (func
    ('symbol', 'rs')
    None)
  hg: parse error: invalid number of arguments: 0
  [255]
  $ try 'rs(2)'
  (func
    ('symbol', 'rs')
    ('symbol', '2'))
  hg: parse error: invalid number of arguments: 1
  [255]
  $ try 'rs(2, data, 7)'
  (func
    ('symbol', 'rs')
    (list
      (list
        ('symbol', '2')
        ('symbol', 'data'))
      ('symbol', '7')))
  hg: parse error: invalid number of arguments: 3
  [255]
  $ try 'rs4(2 or 3, x, x, date)'
  (func
    ('symbol', 'rs4')
    (list
      (list
        (list
          (or
            ('symbol', '2')
            ('symbol', '3'))
          ('symbol', 'x'))
        ('symbol', 'x'))
      ('symbol', 'date')))
  (func
    ('symbol', 'reverse')
    (func
      ('symbol', 'sort')
      (list
        (or
          ('symbol', '2')
          ('symbol', '3'))
        ('symbol', 'date'))))
  3
  2

issue2549 - correct optimizations

  $ log 'limit(1 or 2 or 3, 2) and not 2'
  1
  $ log 'max(1 or 2) and not 2'
  $ log 'min(1 or 2) and not 1'
  $ log 'last(1 or 2, 1) and not 2'

tests for 'remote()' predicate:
#.  (csets in remote) (id)            (remote)
1.  less than local   current branch  "default"
2.  same with local   specified       "default"
3.  more than local   specified       specified

  $ hg clone --quiet -U . ../remote3
  $ cd ../remote3
  $ hg update -q 7
  $ echo r > r
  $ hg ci -Aqm 10
  $ log 'remote()'
  7
  $ log 'remote("a-b-c-")'
  2
  $ cd ../repo
  $ log 'remote(".a.b.c.", "../remote3")'

  $ cd ..

test author/desc/keyword in problematic encoding
# unicode: cp932:
# u30A2    0x83 0x41(= 'A')
# u30C2    0x83 0x61(= 'a')

  $ hg init problematicencoding
  $ cd problematicencoding

  $ python > setup.sh <<EOF
  > print u'''
  > echo a > text
  > hg add text
  > hg --encoding utf-8 commit -u '\u30A2' -m none
  > echo b > text
  > hg --encoding utf-8 commit -u '\u30C2' -m none
  > echo c > text
  > hg --encoding utf-8 commit -u none -m '\u30A2'
  > echo d > text
  > hg --encoding utf-8 commit -u none -m '\u30C2'
  > '''.encode('utf-8')
  > EOF
  $ sh < setup.sh

test in problematic encoding
  $ python > test.sh <<EOF
  > print u'''
  > hg --encoding cp932 log --template '{rev}\\n' -r 'author(\u30A2)'
  > echo ====
  > hg --encoding cp932 log --template '{rev}\\n' -r 'author(\u30C2)'
  > echo ====
  > hg --encoding cp932 log --template '{rev}\\n' -r 'desc(\u30A2)'
  > echo ====
  > hg --encoding cp932 log --template '{rev}\\n' -r 'desc(\u30C2)'
  > echo ====
  > hg --encoding cp932 log --template '{rev}\\n' -r 'keyword(\u30A2)'
  > echo ====
  > hg --encoding cp932 log --template '{rev}\\n' -r 'keyword(\u30C2)'
  > '''.encode('cp932')
  > EOF
  $ sh < test.sh
  0
  ====
  1
  ====
  2
  ====
  3
  ====
  0
  2
  ====
  1
  3

  $ cd ..