jenkins-bot has submitted this change and it was merged. ( https://gerrit.wikimedia.org/r/364423 )

Change subject: site.categorymembers: Support cmstartsortkeyprefix API parameter ......................................................................

site.categorymembers: Support cmstartsortkeyprefix API parameter

site.py: - Fix the docstring for `startsort` and `endsort`. They are in binary string format and cannot be compared with a title directly. Also mention that they are deprecated in MW 1.24. - Add two new parameters, `startprefix` and `endprefix`, to be passed to API as `cmstartsortkeyprefix` and `cmendsortkeyprefix`. The old `startsort` is passed to API as `cmstartsortkey` which is deprecated and is not compatible with `cmstartsortkeyprefix`. Also working with `startsort` is difficult as it should be a "binary string" usually obtained via API or directly from the database. (See T74101)

page.py: - Add the new parameters to `Category.articles`.

Bug: T170265 Change-Id: I08f4a7a4bb1bbe5c10fe678cc7a951a273f61d07 --- M pywikibot/page.py M pywikibot/site.py 2 files changed, 64 insertions(+), 15 deletions(-)

Approvals: Xqt: Looks good to me, approved jenkins-bot: Verified

diff --git a/pywikibot/page.py b/pywikibot/page.py index 6b4d8cf..97f03e1 100644 --- a/pywikibot/page.py +++ b/pywikibot/page.py @@ -2802,7 +2802,9 @@ def articles(self, recurse=False, total=None, content=False, namespaces=None, sortby=None, reverse=False, starttime=None, endtime=None, - startsort=None, endsort=None): + startsort=None, endsort=None, + startprefix=None, endprefix=None, + ): """ Yield all articles in the current category.

@@ -2833,12 +2835,22 @@ @param endtime: if provided, only generate pages added before this time; not valid unless sortby="timestamp" @type endtime: pywikibot.Timestamp - @param startsort: if provided, only generate pages >= this title - lexically; not valid if sortby="timestamp" + @param startsort: if provided, only generate pages that have a + sortkey >= startsort; not valid if sortby="timestamp" + (Deprecated in MW 1.24) @type startsort: str - @param endsort: if provided, only generate pages <= this title - lexically; not valid if sortby="timestamp" + @param endsort: if provided, only generate pages that have a + sortkey <= endsort; not valid if sortby="timestamp" + (Deprecated in MW 1.24) @type endsort: str + @param startprefix: if provided, only generate pages >= this title + lexically; not valid if sortby="timestamp"; overrides "startsort" + (requires MW 1.18+) + @type startprefix: str + @param endprefix: if provided, only generate pages < this title + lexically; not valid if sortby="timestamp"; overrides "endsort" + (requires MW 1.18+) + @type endprefix: str """ for member in self.site.categorymembers(self, namespaces=namespaces, @@ -2849,6 +2861,8 @@ endtime=endtime, startsort=startsort, endsort=endsort, + startprefix=startprefix, + endprefix=endprefix, member_type=['page', 'file'] ): yield member @@ -2868,7 +2882,9 @@ starttime=starttime, endtime=endtime, startsort=startsort, - endsort=endsort + endsort=endsort, + startprefix=startprefix, + endprefix=endprefix, ): yield article if total is not None: diff --git a/pywikibot/site.py b/pywikibot/site.py index 88f48eb..e5bc29a 100644 --- a/pywikibot/site.py +++ b/pywikibot/site.py @@ -3811,7 +3811,9 @@ def categorymembers(self, category, namespaces=None, sortby=None, reverse=False, starttime=None, endtime=None, startsort=None, endsort=None, total=None, - content=False, member_type=None): + content=False, member_type=None, + startprefix=None, endprefix=None, + ): """Iterate members of specified category.

@param category: The Category to iterate. @@ -3833,13 +3835,22 @@ @type starttime: pywikibot.Timestamp @param endtime: if provided, only generate pages added before this time; not valid unless sortby="timestamp" - @type endtime: pywikibot.Timestamp - @param startsort: if provided, only generate pages >= this title - lexically; not valid if sortby="timestamp" + @param startsort: if provided, only generate pages that have a + sortkey >= startsort; not valid if sortby="timestamp" + (Deprecated in MW 1.24) @type startsort: str - @param endsort: if provided, only generate pages <= this title - lexically; not valid if sortby="timestamp" + @param endsort: if provided, only generate pages that have a + sortkey <= endsort; not valid if sortby="timestamp" + (Deprecated in MW 1.24) @type endsort: str + @param startprefix: if provided, only generate pages >= this title + lexically; not valid if sortby="timestamp"; overrides "startsort" + (requires MW 1.18+) + @type startprefix: str + @param endprefix: if provided, only generate pages < this title + lexically; not valid if sortby="timestamp"; overrides "endsort" + (requires MW 1.18+) + @type endprefix: str @param content: if True, load the current content of each iterated page (default False) @type content: bool @@ -3849,6 +3860,8 @@ @type member_type: str or iterable of str; values: page, subcat, file

@raises KeyError: a namespace identifier was not resolved + @raises NotImplementedError: startprefix or endprefix parameters are + given but site.version is less than 1.18. @raises TypeError: a namespace identifier has an inappropriate type such as NoneType or bool """ @@ -3868,7 +3881,10 @@ if starttime and endtime and starttime > endtime: raise ValueError( "categorymembers: starttime must be before endtime") - if startsort and endsort and startsort > endsort: + if startprefix and endprefix and startprefix > endprefix: + raise ValueError( + 'categorymembers: startprefix must be less than endprefix') + elif startsort and endsort and startsort > endsort: raise ValueError( "categorymembers: startsort must be less than endsort")

@@ -3923,6 +3939,7 @@ # sort; we take care of this reversal for the user (starttime, endtime) = (endtime, starttime) (startsort, endsort) = (endsort, startsort) + (startprefix, endprefix) = (endprefix, startprefix) if starttime and sortby == "timestamp": cmargs["gcmstart"] = starttime elif starttime: @@ -3933,12 +3950,28 @@ elif endtime: raise ValueError("categorymembers: " "invalid combination of 'sortby' and 'endtime'") - if startsort and sortby != "timestamp": + if startprefix and sortby != 'timestamp': + if self.version() < MediaWikiVersion('1.18'): + raise NotImplementedError( + 'categorymembers: "startprefix" requires MW 1.18+') + cmargs['gcmstartsortkeyprefix'] = startprefix + elif startprefix: + raise ValueError('categorymembers: invalid combination of ' + "'sortby' and 'startprefix'") + elif startsort and sortby != 'timestamp': cmargs["gcmstartsortkey"] = startsort elif startsort: raise ValueError("categorymembers: " "invalid combination of 'sortby' and 'startsort'") - if endsort and sortby != "timestamp": + if endprefix and sortby != 'timestamp': + if self.version() < MediaWikiVersion('1.18'): + raise NotImplementedError( + 'categorymembers: "endprefix" requires MW 1.18+') + cmargs['cmendsortkeyprefix'] = endprefix + elif endprefix: + raise ValueError('categorymembers: ' + "invalid combination of 'sortby' and 'endprefix'") + elif endsort and sortby != 'timestamp': cmargs["gcmendsortkey"] = endsort elif endsort: raise ValueError("categorymembers: "