#require no-reposimplestore

#testcases revlogv1 revlogv2

#if revlogv2

  $ cat >> $HGRCPATH <<EOF

  > [experimental]

  > revlogv2=enable-unstable-format-and-corrupt-my-data

  > EOF

#endif

  $ cp $HGRCPATH $HGRCPATH.orig

Create repo with unimpeachable content

  $ hg init r

  $ cd r

  $ echo 'Initially untainted file' > target

  $ echo 'Normal file here' > bystander

  $ hg add target bystander

  $ hg ci -m init

Clone repo so we can test pull later

  $ cd ..

  $ hg clone r rpull

  updating to branch default

  2 files updated, 0 files merged, 0 files removed, 0 files unresolved

  $ cd r

Introduce content which will ultimately require censorship. Name the first

censored node C1, second C2, and so on

  $ echo 'Tainted file' > target

  $ echo 'Passwords: hunter2' >> target

  $ hg ci -m taint target

  $ C1=`hg id --debug -i`

  $ echo 'hunter3' >> target

  $ echo 'Normal file v2' > bystander

  $ hg ci -m moretaint target bystander

  $ C2=`hg id --debug -i`

Add a new sanitized versions to correct our mistake. Name the first head H1,

the second head H2, and so on

  $ echo 'Tainted file is now sanitized' > target

  $ hg ci -m sanitized target

  $ H1=`hg id --debug -i`

  $ hg update -r $C2

  1 files updated, 0 files merged, 0 files removed, 0 files unresolved

  $ echo 'Tainted file now super sanitized' > target

  $ hg ci -m 'super sanitized' target

  created new head

  $ H2=`hg id --debug -i`

Verify target contents before censorship at each revision

  $ hg cat -r $H1 target | head -n 10

  Tainted file is now sanitized

  $ hg cat -r $H2 target | head -n 10

  Tainted file now super sanitized

  $ hg cat -r $C2 target | head -n 10

  Tainted file

  Passwords: hunter2

  hunter3

  $ hg cat -r $C1 target | head -n 10

  Tainted file

  Passwords: hunter2

  $ hg cat -r 0 target | head -n 10

  Initially untainted file

Censor revision with 2 offenses

(this also tests file pattern matching: path relative to cwd case)

  $ mkdir -p foo/bar/baz

  $ hg --config extensions.censor= --cwd foo/bar/baz censor -r $C2 -t "remove password" ../../../target

  checking for the censored content in 2 heads

  checking for the censored content in the working directory

  censoring 1 file revisions

  $ hg cat -r $H1 target | head -n 10

  Tainted file is now sanitized

  $ hg cat -r $H2 target | head -n 10

  Tainted file now super sanitized

  $ hg cat -r $C2 target | head -n 10

  abort: censored node: 1e0247a9a4b7

  (set censor.policy to ignore errors)

  $ hg cat -r $C1 target | head -n 10

  Tainted file

  Passwords: hunter2

  $ hg cat -r 0 target | head -n 10

  Initially untainted file

Censor revision with 1 offense

(this also tests file pattern matching: with 'path:' scheme)

  $ hg --config extensions.censor= --cwd foo/bar/baz censor -r $C1 path:target

  checking for the censored content in 2 heads

  checking for the censored content in the working directory

  censoring 1 file revisions

  $ hg cat -r $H1 target | head -n 10

  Tainted file is now sanitized

  $ hg cat -r $H2 target | head -n 10

  Tainted file now super sanitized

  $ hg cat -r $C2 target | head -n 10

  abort: censored node: 1e0247a9a4b7

  (set censor.policy to ignore errors)

  $ hg cat -r $C1 target | head -n 10

  abort: censored node: 613bc869fceb

  (set censor.policy to ignore errors)

  $ hg cat -r 0 target | head -n 10

  Initially untainted file

Can only checkout target at uncensored revisions, -X is workaround for --all

  $ hg revert -r $C2 target | head -n 10

  abort: censored node: 1e0247a9a4b7

  (set censor.policy to ignore errors)

  $ hg revert -r $C1 target | head -n 10

  abort: censored node: 613bc869fceb

  (set censor.policy to ignore errors)

  $ hg revert -r $C1 --all

  reverting bystander

  reverting target

  abort: censored node: 613bc869fceb

  (set censor.policy to ignore errors)

  [255]

  $ hg revert -r $C1 --all -X target

  $ cat target | head -n 10

  Tainted file now super sanitized

  $ hg revert -r 0 --all

  reverting target

  $ cat target | head -n 10

  Initially untainted file

  $ hg revert -r $H2 --all

  reverting bystander

  reverting target

  $ cat target | head -n 10

  Tainted file now super sanitized

Uncensored file can be viewed at any revision

  $ hg cat -r $H1 bystander | head -n 10

  Normal file v2

  $ hg cat -r $C2 bystander | head -n 10

  Normal file v2

  $ hg cat -r $C1 bystander | head -n 10

  Normal file here

  $ hg cat -r 0 bystander | head -n 10

  Normal file here

Can update to children of censored revision

  $ hg update -r $H1

  1 files updated, 0 files merged, 0 files removed, 0 files unresolved

  $ cat target | head -n 10

  Tainted file is now sanitized

  $ hg update -r $H2

  1 files updated, 0 files merged, 0 files removed, 0 files unresolved

  $ cat target | head -n 10

  Tainted file now super sanitized

Set censor policy to abort in trusted $HGRC so hg verify fails

  $ cp $HGRCPATH.orig $HGRCPATH

  $ cat >> $HGRCPATH <<EOF

  > [censor]

  > policy = abort

  > EOF

Repo fails verification due to censorship

  $ hg verify

  checking changesets

  checking manifests

  crosschecking files in changesets and manifests

  checking files

   target@1: censored file data

   target@2: censored file data

  not checking dirstate because of previous errors

  checked 5 changesets with 7 changes to 2 files

  2 integrity errors encountered!

  (first damaged changeset appears to be 1)

  [1]

Cannot update to revision with censored data

  $ hg update -r $C2

  abort: censored node: 1e0247a9a4b7

  (set censor.policy to ignore errors)

  [255]

  $ hg update -r $C1

  abort: censored node: 613bc869fceb

  (set censor.policy to ignore errors)

  [255]

  $ hg update -r 0

  2 files updated, 0 files merged, 0 files removed, 0 files unresolved

  $ hg update -r $H2

  2 files updated, 0 files merged, 0 files removed, 0 files unresolved

Set censor policy to ignore in trusted $HGRC so hg verify passes

  $ cp $HGRCPATH.orig $HGRCPATH

  $ cat >> $HGRCPATH <<EOF

  > [censor]

  > policy = ignore

  > EOF

Repo passes verification with warnings with explicit config

  $ hg verify -q

May update to revision with censored data with explicit config

  $ hg update -r $C2

  1 files updated, 0 files merged, 0 files removed, 0 files unresolved

  $ cat target | head -n 10

  $ hg update -r $C1

  2 files updated, 0 files merged, 0 files removed, 0 files unresolved

  $ cat target | head -n 10

  $ hg update -r 0

  1 files updated, 0 files merged, 0 files removed, 0 files unresolved

  $ cat target | head -n 10

  Initially untainted file

  $ hg update -r $H2

  2 files updated, 0 files merged, 0 files removed, 0 files unresolved

  $ cat target | head -n 10

  Tainted file now super sanitized

Can merge in revision with censored data. Test requires one branch of history

with the file censored, but we can't censor at a head, so advance H1.

  $ hg update -r $H1

  1 files updated, 0 files merged, 0 files removed, 0 files unresolved

  $ C3=$H1

  $ echo 'advanced head H1' > target

  $ hg ci -m 'advance head H1' target

  $ H1=`hg id --debug -i`

  $ hg --config extensions.censor= censor -r $C3 target

  checking for the censored content in 2 heads

  checking for the censored content in the working directory

  censoring 1 file revisions

  $ hg update -r $H2

  1 files updated, 0 files merged, 0 files removed, 0 files unresolved

  $ hg merge -r $C3

  merging target

  0 files updated, 1 files merged, 0 files removed, 0 files unresolved

  (branch merge, don't forget to commit)

Revisions present in repository heads may not be censored

  $ hg update -C -r $H2

  1 files updated, 0 files merged, 0 files removed, 0 files unresolved

  $ hg --config extensions.censor= censor -r $H2 target

  checking for the censored content in 2 heads

  abort: cannot censor file in heads (78a8fc215e79)

  (clean/delete and commit first)

  [255]

  $ echo 'twiddling thumbs' > bystander

  $ hg ci -m 'bystander commit'

  $ H2=`hg id --debug -i`

  $ hg --config extensions.censor= censor -r "$H2^" target

  checking for the censored content in 2 heads

  abort: cannot censor file in heads (efbe78065929)

  (clean/delete and commit first)

  [255]

Cannot censor working directory

  $ echo 'seriously no passwords' > target

  $ hg ci -m 'extend second head arbitrarily' target

  $ H2=`hg id --debug -i`

  $ hg update -r "$H2^"

  1 files updated, 0 files merged, 0 files removed, 0 files unresolved

  $ hg --config extensions.censor= censor -r . target

  checking for the censored content in 2 heads

  checking for the censored content in the working directory

  abort: cannot censor working directory

  (clean/delete/update first)

  [255]

  $ hg update -r $H2

  1 files updated, 0 files merged, 0 files removed, 0 files unresolved

Can re-add file after being deleted + censored

  $ C4=$H2

  $ hg rm target

  $ hg ci -m 'delete target so it may be censored'

  $ H2=`hg id --debug -i`

  $ hg --config extensions.censor= censor -r $C4 target

  checking for the censored content in 2 heads

  checking for the censored content in the working directory

  censoring 1 file revisions

  $ hg cat -r $C4 target | head -n 10

  $ hg cat -r "$H2^^" target | head -n 10

  Tainted file now super sanitized

  $ echo 'fresh start' > target

  $ hg add target

  $ hg ci -m reincarnated target

  $ H2=`hg id --debug -i`

  $ hg cat -r $H2 target | head -n 10

  fresh start

  $ hg cat -r "$H2^" target | head -n 10

  target: no such file in rev 452ec1762369

  $ hg cat -r $C4 target | head -n 10

  $ hg cat -r "$H2^^^" target | head -n 10

  Tainted file now super sanitized

Can censor enough revision to move back to inline storage

  $ hg debugrevlogstats | grep target

  rev-count   data-size inl type      target 

          8         ??? no  file      target (glob) (revlogv2 !)

          8         ??? yes file      target (glob) (revlogv1 !)

  $ $TESTDIR/seq.py 4000 | $TESTDIR/sha256line.py > target

  $ hg ci -m 'add 100k passwords'

  $ H2=`hg id --debug -i`

  $ C5=$H2

  $ hg revert -r "$H2^" target

  $ hg ci -m 'cleaned 100k passwords'

  $ H2=`hg id --debug -i`

  $ hg debugrevlogstats | grep target

  rev-count   data-size inl type      target 

         10      ?????? no  file      target (glob)

  $ hg --config extensions.censor= censor -r $C5 target

  checking for the censored content in 2 heads

  checking for the censored content in the working directory

  censoring 1 file revisions

The important part is for the censor operation to not crash and the repository

to not be corrupted.  Right now this involve keeping the revlog split.

  $ hg debugrevlogstats | grep target

  rev-count   data-size inl type      target 

         10         ??? no  file      target (glob)

  $ hg cat -r $C5 target | head -n 10

  $ hg cat -r $H2 target | head -n 10

  fresh start

  $ hg verify

  checking changesets

  checking manifests

  crosschecking files in changesets and manifests

  checking files

  checking dirstate

  checked 12 changesets with 13 changes to 2 files

Repo with censored nodes can be cloned and cloned nodes are censored

  $ cd ..

  $ hg clone r rclone

  updating to branch default

  2 files updated, 0 files merged, 0 files removed, 0 files unresolved

  $ cd rclone

  $ hg cat -r $H1 target | head -n 10

  advanced head H1

  $ hg cat -r $H2~5 target | head -n 10