test-annotate: fix up expected output for pure This is just a side effect of surfacing the "revisions were skipped" state in the blame output. Differential Revision: https://phab.mercurial-scm.org/D956

style: never use a space before a colon or comma Differential Revision: https://phab.mercurial-scm.org/D954

eol: make [eol] config section sensitive for chg confighash The eol extension may mangle the [eol] config section and that means chg is unable to detect config file change (because it re-applies setconfig changes). This makes test-eol.t pass with chg. Differential Revision: https://phab.mercurial-scm.org/D917

test-alias: make it compatible with chg ad1bdea (dispatch: defer environment variable resolution in alias commands (BC), 2016-05-06) made environment variables lazily resolved. But after D805 (alias: make alias command lazily resolved 2017-09-23), alias resolution happened after uisetup, which breaks the test for chg. `uisetup` is known to behave different in chg. Let's verify the feature without using `*setup`. Differential Revision: https://phab.mercurial-scm.org/D912

serve: make tests compatible with chg chg only supports 'hg serve' when the options to the serve command follow the 'hg serve'. For example, 'hg -R <repo> serve ..' is unsupported. This leads to issues with chg running for the following tests: - test-bundle2-exchange.t - test-clone-uncompressed.t - test-hgweb-csp.t - test-http-bad-server.t - test-http-bundle1.t - test-http-protocol.t - test-http.t There was an effort made earlier to fix this issue for chg and the tests were fixed to confirm to the compatible pattern. But the new tests did not take care of the same and hence, fail. Hopefully, there will be continuous build setup for chg after all tests are made compatible with chg so that we can avoid such issues. Test Plan: Ran the aforementioned tests with and without '--chg' option. Differential Revision: https://phab.mercurial-scm.org/D946

ui: convert to/from Optional[bytes] to Optional[str] in password manager This password manager proxy is roughly the right-looking layer to convert between strings and bytes. Many of these arguments can be None, so we have a helper method to make the conversion preserve Nones without exploding. Differential Revision: https://phab.mercurial-scm.org/D886

configitems: register the 'debug.dirstate.delaywrite' config

configitems: register the 'merge.preferancestor' config

configitems: register the 'email.from' config

configitems: register the 'smtp.port' config

configitems: register the 'phases.new-commit' config

configitems: register the 'experimental.histeditng' config

configitems: register the 'experimental.histedit.autoverb' config

configitems: register the 'histedit.singletransaction' config

configitems: register the 'histedit.linelen' config

configitems: register the 'histedit.dropmissing' config

configitems: register the 'histedit.defaultrev' config

configitems: register the 'transplant.log' config

configitems: register the 'transplant.filter' config

urllibcompat: move some adapters from pycompat to urllibcompat These are all the httpserver and urllib.* aliases. They seem to make more sense in the slightly-more-specific urllibcompat package than the general-purpose pycompat. Differential Revision: https://phab.mercurial-scm.org/D935

cleanup: use urllibcompat for renamed methods on urllib request objects Differential Revision: https://phab.mercurial-scm.org/D891

urllibcompat: new library to help abstract out some python3 urllib2 stuff Doing a new file instead of pycompat because I'm starting to feel like pycompat is getting a little enormous in terms of scope. Differential Revision: https://phab.mercurial-scm.org/D890

test-devel-warnings: make the test compatible with chg The test fails when run with the "--chg" option. Therefore, this commit makes it compatible with chg. Test Plan: Ran the test "test-devel-warnings.t' with and without the "--chg" option Differential Revision: https://phab.mercurial-scm.org/D915

fsmonitor: use configitem We might as well get this out of the way. Differential Revision: https://phab.mercurial-scm.org/D893

fsmonitor: access copymap in new location fsmonitor has been busted since 0865d25e8a8a due to moving self._copymap. Fix it. Differential Revision: https://phab.mercurial-scm.org/D892

extdata: use subprocess so we don't have to chdir() manually

extdata: just use iterator to read lines one by one

extdata: ignore ambiguous identifier as well

templater: add experimental support for extdata This is minimal and non-controversial implementation of extdata() template function. Originally extdata sources were exposed to the keyword namespace, but I've changed it to a plain function for simplicity.

revset: add experimental support for extdata This is minimal and non-controversial implementation of extdata() revset. Originally extdata sources were exposed to the symbol namespace, but I've changed it to a plain function for simplicity.

extdata: add extdatasource reader This adds basic support for extdata, a way to add external data sources for revsets and templates. An extdata data source is simply a list of lines of the form: <revision identifier>[<space><freeform text>]\n An extdata source is configured thusly: [extdata] name = <a url or path> urls of the form shell: are launch shell commands to generate data. This patch is slightly modified by Yuya Nishihara as follows: - fix typo - remove unused function - remove future expansion point for parameter (which can be added later as the extdata revset/template are experimental) You can see the original patch at https://www.mercurial-scm.org/pipermail/mercurial-devel/2016-September/088426.html

tests: change to parent directory before all "hg init" in test-log.t Add a "cd .." before the second "hg init" so that all repositories are on top level of test directory. Makes inspection of test directory easier.

config: add a missing preparewrite() call Thanks Yuya for pointing this out in D808. Differential Revision: https://phab.mercurial-scm.org/D924

test-strip: make test compatible with chg The test was using reposetup which had the logic for stripping commits. This leads to a situation where if the reposetup was called twice for an extension (which can happen with chg running), the stripped node would not be found the second time. Therefore, this commit changes the test to put the stripping logic inside commands instead of the reposetup. This ensures that the stripping logic is invoked only when the command is invoked and thus, avoids any problems. Test Plan: Ran the test 'test-strip.t' with and without the '--chg' option. Differential Revision: https://phab.mercurial-scm.org/D928

test-hook: make test compatible with chg The test uses the 'print' method instead of writing to stdout using 'ui.write' which leads to incompatibility with chg. This commit modifies the test to use 'ui' instead which fixes the problem. Test Plan: Ran the test 'test-hook.t' with and without '--chg' option. Differential Revision: https://phab.mercurial-scm.org/D927

test-setdiscovery: make test compatible with chg The test checks the output of the blackbox extension which will contain logs corresponding to chg in case chg is running. Therefore, this commit modifies the test to take chg into consideration while working with the blackbox extension. Test Plan: Ran the test 'test-setdiscovery.t' with and without the '--chg' option. Differential Revision: https://phab.mercurial-scm.org/D926

test-merge-subrepos: make test compatible with chg The test checks the output of '.hg/blackbox.log' which will contain logs corresponding to chg in case chg is running. Therefore, this commit modifies the test to take chg into consideration while checking the blackbox.log contents. Test Plan: Ran the test 'test-merge-subrepos.t' with and without the '--chg' option. Differential Revision: https://phab.mercurial-scm.org/D925

test-convert-cvs: make test compatible with chg The test uses the 'print' method instead of writing to stdout using 'ui.write' which leads to incompatibility with chg. This commit modifies the test to use the 'ui' object instead which fixes the problem. Test Plan: Ran the test 'test-convert-cvs.t' with and without '--chg' option. Differential Revision: https://phab.mercurial-scm.org/D923

test-basic: make test compatible with chg The error codes returned when writing to /dev/full are different after the first failure with and without '--chg' option. Therefore, this commit conditionally handles the error codes as appropriate. Test Plan: Ran the test 'test-basic.t' with and without '--chg' option. Differential Revision: https://phab.mercurial-scm.org/D922

zeroconf: do not crash if socket being read is closed by another thread In zeroconf/__init__.py, there is: server = Zeroconf.Zeroconf(ip) l = listener() Zeroconf.ServiceBrowser(server, "_hg._tcp.local.", l) time.sleep(1) server.close() `server.close()` closes the underlying socket while the `ServiceBrowser` may still have a background thread reading the socket. There could be a race condition where the reading thread reads the closed socket, resulting in EBADF crash. This patch catches the exception. This makes test-paths.t pass with chg. Differential Revision: https://phab.mercurial-scm.org/D919

test-revlog-mmapindex: make it compatible with chg The test misses an explicit flush(). Differential Revision: https://phab.mercurial-scm.org/D918

test-profile: gate chg-incompatible part with '#if chg' chg has a different extension loading logic, which affects the profiler extension test case. Gate the block with '#if chg' so the test passes with chg. Differential Revision: https://phab.mercurial-scm.org/D916

test-logtoprocess: make it compatible with chg chg runs more commands and outputs more lines. This patch matches them. Differential Revision: https://phab.mercurial-scm.org/D914

test-globalopts: make the test compatible with chg The test fails when run with the '--chg' option. Therefore, this commit modifies the test to make it compatible with chg. Test Plan: Ran 'test-globalopts.t' with and without the '--chg' option. Differential Revision: https://phab.mercurial-scm.org/D913

test-pager: make it compatible with chg chg's runpager implementation is different. It behaves differently for the "shell=False, command not found" case. Differential Revision: https://phab.mercurial-scm.org/D911

changelog: use a Factory for default value for files The default value is compiled into the generated type. This means that default values are shared between instances. For immutable types like bool, str, int, and tuple, this is fine. But for mutable types like list and dict, we need to use attr.Factory() to instantiate a new instance of the default for each object. Differential Revision: https://phab.mercurial-scm.org/D901

cext: wrap before brace for functions This is our prevailing style. Differential Revision: https://phab.mercurial-scm.org/D910

cext: put case statements on separate line This seems to be the prevailing style, even though it is a bit more verbose for very simple switch statements. Differential Revision: https://phab.mercurial-scm.org/D909

cext: reorder #include We mostly abide by this style. In one case, a blank line was inserted to prevent a local `#include "file"` from coming before a `#include <file>`. Differential Revision: https://phab.mercurial-scm.org/D908

cext: move braces for control statements to same line This seems to be the prevailing style in the code by a wide margin. Differential Revision: https://phab.mercurial-scm.org/D907

registrar: fixing typo in comment I was just going through the module and noticed the typo. This commit fixes 'onfalure' -> 'onfailure'. Differential Revision: https://phab.mercurial-scm.org/D906

style: never put multiple statements on one line Differential Revision: https://phab.mercurial-scm.org/D905

annotate: mark lines affected by skip-annotate with * This is to prevent weird surprises from happening with skips being attributed to the wrong changeset. .. feature:: `hg annotate --skip` now prints a `*` on lines with skipped revisions Differential Revision: https://phab.mercurial-scm.org/D900

annotate: track whether a particular annotation was the result of a skip We're going to expose this information in the UI in an upcoming patch. Differential Revision: https://phab.mercurial-scm.org/D899

annotate: introduce attr for storing per-line annotate data We're going to extend this a bit -- at first by simply adding whether this was a skipped child. We're well on our way to outgrowing tuples, though -- adding more and more fields to tuples becomes annoying very quickly. Differential Revision: https://phab.mercurial-scm.org/D898

context: rename local 'attr' to 'attr_' In the next diff we're going to import mercurial.thirdparty.attr, and pyflakes complains about this if this rename isn't done. Differential Revision: https://phab.mercurial-scm.org/D897

annotate: move annotatepair unit tests to a separate file In upcoming patches the output is going to be significantly longer than it is today, and doctests don't allow wrapping the output. Differential Revision: https://phab.mercurial-scm.org/D896

check-code: allow an exception for camelcase where required unittest has a `maxDiff` parameter which has to be set to `None` in order for large enough failure diffs to be displayed. Add a comment to disable the camelcase check for `self.maxDiff = None` lines. Differential Revision: https://phab.mercurial-scm.org/D895

url: use native strings for header values Differential Revision: https://phab.mercurial-scm.org/D889

keepalive: python 3 portability tweaks Differential Revision: https://phab.mercurial-scm.org/D888

httppasswordmgrdbproxy: specify exact arguments We only ever call these functions in a single way, so let's just actually specify them. We need to do some string/bytes encoding dancing here for Python 3, so it'll help to know what arguments we need to convert. # no-check-commit because I'm modifying functions that check-commit does not like. Differential Revision: https://phab.mercurial-scm.org/D885

formatter: fix default list/dict generator to be evaluated more than once Before, _hybrid.gen must be a generator which could be consumed only once. It was okay in templatekw.py since template keywords are functions which create temporary hybrid objects, but the formatter doesn't work in that way. To work around the issue, this patch makes _hybrid.gen optionally be a function returning a generator. Thanks to Pulkit for finding this issue.

doctest: drop hack to run py2/3 tests selectively All doctests pass on Python 3.

docker: try to follow the best practices for writing Dockerfiles Merged multiple RUN instructions and sorted the arguments alphabetically Reference: https://docs.docker.com/engine/userguide/eng-image/dockerfile_best-practices/