(index, pagetitle, form, II))
remove_param("II")
III = getparam(template, "III")
if III == u"ء":
msg("Page %s %s: form=%s, removing III=%s" %
(index, pagetitle, form, III))
remove_param("III")
newtemp = unicode(template)
if origtemp != newtemp:
msg("Replacing %s with %s" % (origtemp, newtemp))
if len(paramschanged) > 0:
actions_taken.append("form=%s (%s)" %
(form, ', '.join(paramschanged)))
changelog = "ar-verb: remove params: %s" % '; '.join(actions_taken)
#if len(actions_taken) > 0:
msg("Change log = %s" % changelog)
return text, changelog
def clean_verb_headword(save, startFrom, upTo):
for cat in [u"Arabic verbs"]:
for index, page in blib.cat_articles(cat, startFrom, upTo):
blib.do_edit(page, index, clean_one_page_verb_headword, save=save)
pa = blib.init_argparser("Clean up verb headword templates")
params = pa.parse_args()
startFrom, upTo = blib.parse_start_end(params.start, params.end)
clean_verb_headword(params.save, startFrom, upTo)
if len(newtext) - len(text) != len(to_template) - len(
from_template):
pagemsg(
"WARNING: Length mismatch when undoing Greek param removal, may have matched multiple templates: from=%s, to=%s"
% (from_template, to_template))
changelog = "Undid removal of %s=%s in %s" % (
removed_param, param_value, to_template)
pagemsg("Change log = %s" % changelog)
return newtext, changelog
page = pywikibot.Page(site, pagename)
if not page.exists():
msg("Page %s %s: WARNING, something wrong, does not exist" %
(index, pagename))
else:
blib.do_edit(page,
index,
undo_one_page_greek_removal,
save=save,
verbose=verbose)
pa = blib.init_argparser("Undo Greek transliteration removal")
pa.add_argument(
"--file", help="File containing templates and removal directives to undo")
params = pa.parse_args()
startFrom, upTo = blib.parse_start_end(params.start, params.end)
undo_greek_removal(params.save, params.verbose, params.file, startFrom, upTo)
pagemsg(
"WARNING: Length mismatch when undoing Russian auto-accenting, may have matched multiple templates: orig=%s, repl=%s"
% (orig_template, repl_template))
changelog = "Undid auto-accenting (per Wikitiki89) of %s" % (
orig_template)
pagemsg("Change log = %s" % changelog)
return newtext, changelog
page = pywikibot.Page(site, pagename)
if not page.exists():
msg("Page %s %s: WARNING, something wrong, does not exist" %
(index, pagename))
else:
blib.do_edit(page,
index,
undo_one_page_ru_auto_accent,
save=save,
verbose=verbose)
pa = blib.init_argparser(
"Undo auto-accent changes involving ux, usex and lang templates that look like direct quotes"
)
pa.add_argument("--file",
help="File containing log file from original auto-accent run")
params = pa.parse_args()
startFrom, upTo = blib.parse_start_end(params.start, params.end)
undo_ru_auto_accent(params.save, params.verbose, params.file, startFrom, upTo)
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program. If not, see <http://www.gnu.org/licenses/>.
import re, codecs
import blib
import ru_translit
from canon_foreign import canon_links
pa = blib.init_argparser("Canonicalize Russian and translit")
pa.add_argument(
"--cattype",
default="borrowed",
help="""Categories to examine ('vocab', 'borrowed', 'translation',
'links', 'pagetext', 'pages', an arbitrary category or comma-separated list)"""
)
pa.add_argument(
"--page-file",
help="""File containing "pages" to process when --cattype pagetext,
or list of pages when --cattype pages""")
params = pa.parse_args()
startFrom, upTo = blib.parse_start_end(params.start, params.end)
pages_to_do = []
if params.page_file:
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program. If not, see <http://www.gnu.org/licenses/>.
import re, codecs
import blib
import ru_translit
from canon_foreign import canon_links
pa = blib.init_argparser("Canonicalize Russian and translit")
pa.add_argument("--cattype", default="borrowed",
help="""Categories to examine ('vocab', 'borrowed', 'translation',
'links', 'pagetext', 'pages' or comma-separated list)""")
pa.add_argument("--page-file",
help="""File containing "pages" to process when --cattype pagetext,
or list of pages when --cattype pages""")
params = pa.parse_args()
startFrom, upTo = blib.parse_start_end(params.start, params.end)
pages_to_do = []
if params.page_file:
for line in codecs.open(params.page_file, "r", encoding="utf-8"):
line = line.strip()
if params.cattype == "pages":
pages_to_do.append(line)
rmparam(t, "f")
ftr = getparam(t, "ftr")
rmparam(t, "ftr")
addparam(t, "1", head)
if tr:
addparam(t, "tr", tr)
if f:
addparam(t, "f", f)
if ftr:
addparam(t, "ftr", ftr)
if pl:
addparam(t, "pl", pl)
if pltr:
addparam(t, "pltr", pltr)
if sort:
addparam(t, "sort", sort)
temps_changed.append("arz-adj")
return text, "rewrite %s to new style" % ", ".join(temps_changed)
def rewrite_arz_headword(save, verbose, startFrom, upTo):
for cat in [u"Egyptian Arabic adjectives", "Egyptian Arabic nouns"]:
for index, page in blib.cat_articles(cat, startFrom, upTo):
blib.do_edit(page, index, rewrite_one_page_arz_headword, save=save,
verbose=verbose)
pa = blib.init_argparser("Rewrite Egyptian Arabic headword templates")
params = pa.parse_args()
startFrom, upTo = blib.parse_start_end(params.start, params.end)
rewrite_arz_headword(params.save, params.verbose, startFrom, upTo)
def rewrite_one_page_ar_nisba(page, index, text):
for template in text.filter_templates():
if template.name == "ar-nisba":
if template.has("head") and not template.has(1):
head = unicode(template.get("head").value)
template.remove("head")
addparam(template,
"1",
head,
before=template.params[0].name
if len(template.params) > 0 else None)
if template.has("plhead"):
blib.msg("%s has plhead=" % page.title())
return text, "ar-nisba: head= -> 1="
def rewrite_ar_nisba(save, verbose, startFrom, upTo):
for index, page in blib.references("Template:ar-nisba", startFrom, upTo):
blib.do_edit(page,
index,
rewrite_one_page_ar_nisba,
save=save,
verbose=verbose)
pa = blib.init_argparser("Rewrite ar-nisba, changing head= to 1=")
params = pa.parse_args()
startFrom, upTo = blib.parse_start_end(params.start, params.end)
rewrite_ar_nisba(params.save, params.verbose, startFrom, upTo)
remove_param("I")
II = getparam(template, "II")
if (II == u"ء" or II in [u"و", u"ي"] and
form in ["2", "II", "3", "III", "5", "V", "6", "VI"]):
msg("Page %s %s: form=%s, removing II=%s" % (index, pagetitle, form, II))
remove_param("II")
III = getparam(template, "III")
if III == u"ء":
msg("Page %s %s: form=%s, removing III=%s" % (index, pagetitle, form, III))
remove_param("III")
newtemp = unicode(template)
if origtemp != newtemp:
msg("Replacing %s with %s" % (origtemp, newtemp))
if len(paramschanged) > 0:
actions_taken.append("form=%s (%s)" % (form, ', '.join(paramschanged)))
changelog = "ar-verb: remove params: %s" % '; '.join(actions_taken)
#if len(actions_taken) > 0:
msg("Change log = %s" % changelog)
return text, changelog
def clean_verb_headword(save, startFrom, upTo):
for cat in [u"Arabic verbs"]:
for page, index in blib.cat_articles(cat, startFrom, upTo):
blib.do_edit(page, index, clean_one_page_verb_headword, save=save)
pa = blib.init_argparser("Clean up verb headword templates")
params = pa.parse_args()
startFrom, upTo = blib.parse_start_end(params.start, params.end)
clean_verb_headword(params.save, startFrom, upTo)
else:
pages_to_ignore = set()
for category in yield_cats():
msg("Processing category %s ..." % category)
errmsg("Processing category %s ..." % category)
for index, page in blib.cat_articles(category, startFrom, upTo):
if page.title() not in pages_to_ignore:
blib.do_edit(page,
index,
remove_translit_one_page,
save=params.save,
verbose=params.verbose)
pa = blib.init_argparser(
"Remove translit, sc= from hy, xcl, ka, el, grc templates")
pa.add_argument("--langs",
default="all",
help="Languages to do, a comma-separated list or 'all'")
pa.add_argument("--cattype",
default="all",
help="""Categories to examine ('all' or comma-separated list of
'translit', 'lemma', 'non-lemma'; default 'all')""")
pa.add_argument(
"--ignore-lemma-non-lemma",
action="store_true",
help=
"""Ignore lemma and non-lemma pages (useful with '--cattype translit').""")
pa.add_argument("--do-head",
action="store_true",
help="""Remove tr= in {{head|..}}""")
tname, tlang, "sc", scvalue))
oldtempl = "%s" % unicode(template)
template.remove("sc")
pagemsg("Replaced %s with %s" % (oldtempl, unicode(template)))
newresult = ["remove %s.%s.sc=%s" % (tname, tlang, scvalue)]
if result != False:
result = result + newresult
else:
result = newresult
return result
return blib.process_links(save, verbose, lang, longlang, cattype,
startFrom, upTo, process_param, sort_group_changelogs,
pages_to_do=pages_to_do)
pa = blib.init_argparser("Remove redundant foreign translit and script")
pa.add_argument("--lang",
help="""Language to use when --cattype is 'vocab' or 'borrowed'.""")
pa.add_argument("--cattype", default="borrowed",
help="""Categories to examine ('vocab', 'borrowed', 'translation',
'links', 'pagetext', 'pages', an arbitrary category or comma-separated list)""")
pa.add_argument("--page-file",
help="""File containing "pages" to process when --cattype pagetext,
or list of pages when --cattype pages""")
params = pa.parse_args()
startFrom, upTo = blib.parse_start_end(params.start, params.end)
pages_to_do = []
if params.page_file:
for line in codecs.open(params.page_file, "r", encoding="utf-8"):
line = line.strip()
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program. If not, see <http://www.gnu.org/licenses/>.
import re, codecs
import blib
import grc_translit
from canon_foreign import canon_links
pa = blib.init_argparser("Canonicalize Greek and translit")
pa.add_argument("--cattype", default="borrowed",
help="""Categories to examine ('vocab', 'borrowed', 'translation',
'links', 'pagetext', 'pages' or comma-separated list)""")
pa.add_argument("--page-file",
help="""File containing "pages" to process when --cattype pagetext,
or list of pages when --cattype pages""")
params = pa.parse_args()
startFrom, upTo = blib.parse_start_end(params.start, params.end)
pages_to_do = []
if params.page_file:
for line in codecs.open(params.page_file, "r", encoding="utf-8"):
line = line.strip()
if params.cattype == "pages":
pages_to_do.append(line)
for vn in vns:
no_i3rab_vns.append(remove_i3rab(pagename, index, verbid, vn))
newvn = ",".join(no_i3rab_vns)
if uncertain:
newvn += "?"
if newvn != vnvalue:
msg("Page %s %s: Verb %s, replacing %s with %s" % (
index, pagename, verbid, vnvalue, newvn))
addparam(template, "vn", newvn)
verbids.append(verbid)
return text, "Remove i3rab from verbal nouns for verb(s) %s" % (
', '.join(verbids))
for index, page in blib.cat_articles("Arabic verbs", startFrom, upTo):
blib.do_edit(page, index, do_one_page_verb, save=save, verbose=verbose)
pa = blib.init_argparser("Remove i3rab")
pa.add_argument("--verb", action='store_true',
help="Do verbal nouns in verbs")
pa.add_argument("--noun", action='store_true',
help="Do arguments in nouns")
params = pa.parse_args()
startFrom, upTo = blib.parse_start_end(params.start, params.end)
if params.noun:
do_nouns(["noun", "adjective"],
["ar-noun", "ar-coll-noun", "ar-sing-noun", "ar-nisba", "ar-noun-nisba",
"ar-adj", "ar-numeral"],
params.save, startFrom, upTo)
if params.verb:
do_verbs(params.save, startFrom, upTo)
removeparams,
is_proper=False):
for index, page in blib.references("Template:%s" % tempname, startFrom,
upTo):
create_declension(page,
index,
save,
pos,
tempname,
decltempname,
sgnum,
removeparams,
is_proper=is_proper)
pa = blib.init_argparser("Create Arabic declensions")
pa.add_argument("--proper", action='store_true', help="Do proper nouns only")
params = pa.parse_args()
startFrom, upTo = blib.parse_start_end(params.start, params.end)
params_to_remove = [
"2", # gender; not included in declension tables
"g2", # second gender; not included in declension tables
"singg", # singulative gender; not included in declension tables
"collg", # collective gender; not included in declension tables
"tr", # transliterations; we check for them in the declension code and
# handle them specially
"cons", # construct state; always predictable and we do it
"dcons", # dual construct state; always predictable and we do it
"pauccons", # paucal construct state; always predictable and we do it
assert((not comment) == (newtext == page.text))
if newtext != page.text:
if verbose:
msg("Replacing [[%s]] with [[%s]]" % (page.text, newtext))
page.text = newtext
msg("For page %s, comment = %s" % (pagename, comment))
if save:
page.save(comment = comment)
def create_declensions(save, pos, tempname, decltempname, sgnum,
startFrom, upTo, removeparams, is_proper=False):
for index, page in blib.references("Template:%s" % tempname, startFrom, upTo):
create_declension(page, index, save, pos, tempname, decltempname, sgnum,
removeparams, is_proper=is_proper)
pa = blib.init_argparser("Create Arabic declensions")
pa.add_argument("--proper", action='store_true',
help="Do proper nouns only")
params = pa.parse_args()
startFrom, upTo = blib.parse_start_end(params.start, params.end)
params_to_remove = [
"2", # gender; not included in declension tables
"g2", # second gender; not included in declension tables
"singg", # singulative gender; not included in declension tables
"collg", # collective gender; not included in declension tables
"tr", # transliterations; we check for them in the declension code and
# handle them specially
"cons", # construct state; always predictable and we do it
"dcons", # dual construct state; always predictable and we do it
startFrom, upTo):
def rewrite_one_page_template_names(page, index, text):
actions = []
for template in text.filter_templates():
if template.name == old:
actions.append("rename {{temp|%s}} to {{temp|%s}}" % (old, new))
template.name = new
for remove in removelist:
if template.has(remove):
template.remove(remove)
actions.append("remove %s=" % remove)
return text, '; '.join(actions)
for index, page in blib.references("Template:%s" % old, startFrom, upTo):
blib.do_edit(page, index, rewrite_one_page_template_names, save=save,
verbose=verbose)
pa = blib.init_argparser("Rewrite old to new template names")
pa.add_argument("-o", "--old", help="Old name of template")
pa.add_argument("-n", "--new", help="New name of template")
pa.add_argument("-r", "--remove", help="Comma-separated template params to remove")
params = pa.parse_args()
startFrom, upTo = blib.parse_start_end(params.start, params.end)
removelist = []
if params.remove:
removelist = re.split(",", params.remove)
rewrite_template_names(params.old, params.new, removelist, params.save,
params.verbose, startFrom, upTo)
else:
pagemsg("Original template found, taking no action")
else:
pagemsg("Replaced %s with %s" % (repl_template, orig_template))
if found_orig_template:
pagemsg("WARNING: Undid replacement, but original template %s already present!" %
orig_template)
if len(newtext) - len(text) != len(orig_template) - len(repl_template):
pagemsg("WARNING: Length mismatch when undoing Russian auto-accenting, may have matched multiple templates: orig=%s, repl=%s" % (
orig_template, repl_template))
changelog = "Undid auto-accenting (per Wikitiki89) of %s" % (orig_template)
pagemsg("Change log = %s" % changelog)
return newtext, changelog
page = pywikibot.Page(site, pagename)
if not page.exists():
msg("Page %s %s: WARNING, something wrong, does not exist" % (
index, pagename))
else:
blib.do_edit(page, index, undo_one_page_ru_auto_accent, save=save,
verbose=verbose)
pa = blib.init_argparser("Undo auto-accent changes involving ux, usex and lang templates that look like direct quotes")
pa.add_argument("--file",
help="File containing log file from original auto-accent run")
params = pa.parse_args()
startFrom, upTo = blib.parse_start_end(params.start, params.end)
undo_ru_auto_accent(params.save, params.verbose, params.file, startFrom, upTo)
(form, getparam(template, str(1 + int(formarg))),
getparam(template, str(2 + int(formarg)))))
else:
actions_taken.append("form=%s" % form)
changelog = "%s: canonicalize form (%s=) to Roman numerals: %s" % (
tempname, formarg, '; '.join(actions_taken))
if len(actions_taken) > 0:
msg("Change log = %s" % changelog)
return text, changelog
for index, page in blib.references("Template:%s" % tempname, startFrom,
upTo):
blib.do_edit(page, index, canonicalize_one_page_verb_form, save=save)
pa = blib.init_argparser("Rewrite form= to 1= in verb headword templates")
pa.add_argument("--headword",
action='store_true',
help="Rewrite form= to 1= in ar-verb and canonicalize")
pa.add_argument(
"--canonicalize",
action='store_true',
help="Canonicalize form in Arabic verb templates other than ar-verb")
params = pa.parse_args()
startFrom, upTo = blib.parse_start_end(params.start, params.end)
if params.headword:
rewrite_verb_headword(params.save, startFrom, upTo)
if params.canonicalize:
canonicalize_verb_form(params.save, startFrom, upTo, "ar-conj", "1")
canonicalize_verb_form(params.save, startFrom, upTo, "ar-past3sm", "1")
actions = []
if idafa_added:
actions.append(u"Replaced ʾidāfa params with idafa= param: %s" % (
", ".join(idafa_added)))
if num_new_style:
actions.append(u"Corrected %s old-style ʾidāfa param(s) to new-style"
% num_new_style)
if num_modhead_changed:
actions.append(u"Changed modN to modheadN")
if num_state_ind_to_ind_def:
actions.append(u"Converted state=ind to state=ind-def for proper noun")
if num_basestate_ind_def:
actions.append(u"Converted state=def|basestate=ind to state=ind-def")
if actions:
changelog = "; ".join(actions)
pagemsg("Changelog = %s" % changelog)
return text, changelog
return text, ""
def rewrite_idafa(save, verbose, startFrom, upTo):
for template in arabic_decl_templates:
for page, index in blib.references("Template:" + template, startFrom, upTo):
blib.do_edit(page, index, rewrite_one_page_idafa, save=save,
verbose=verbose)
pa = blib.init_argparser(u"Rewrite ʾidāfa params with idafa= param, and related changes")
params = pa.parse_args()
startFrom, upTo = blib.parse_start_end(params.start, params.end)
rewrite_idafa(params.save, params.verbose, startFrom, upTo)
for digval, dig in sorted(digits.iteritems(), key=lambda x: x[0]):
msg(
u"""
export.numbers[%s] = {
numeral = "%s٠٠٠",
cardinal = {{"%s", "%s"}},
}"""
% (digval * 1000, dig.eastarabnum, dig.thousand, dig.thousandtr)
)
msg(
u"""
return export"""
)
pa = blib.init_argparser("Save numbers to Wiktionary")
pa.add_argument("--lemmas", action="store_true", help="Do lemmas from 21-99.")
pa.add_argument("--non-lemmas", action="store_true", help="Do non-lemmas from 21-99.")
pa.add_argument("--ordinal-lemmas", action="store_true", help="Do ordinal lemmas from 11-19.")
pa.add_argument("--ordinal-non-lemmas", action="store_true", help="Do ordinal non-lemmas from 11-19.")
pa.add_argument("--number-list-data", action="store_true", help="Output number list data.")
pa.add_argument("--offline", action="store_true", help="Run offline, checking output only.")
params = pa.parse_args()
startFrom, upTo = blib.parse_start_end(params.start, params.end)
def iter_pages(createfn):
for tenval, ten, digval, dig in iter_numerals():
yield createfn(tenval, ten, digval, dig)
def fix_tool_place_noun(save, verbose, startFrom, upTo):
for template in ["ar-tool noun", "ar-noun of place", "ar-instance noun"]:
# Fix the template refs. If cap= is present, remove it; else, add lc=.
def fix_one_page_tool_place_noun(page, index, text):
pagetitle = page.title()
for t in text.filter_templates():
if t.name == template:
if getparam(t, "cap"):
msg("Page %s %s: Template %s: Remove cap=" %
(index, pagetitle, template))
t.remove("cap")
else:
msg("Page %s %s: Template %s: Add lc=1" %
(index, pagetitle, template))
addparam(t, "lc", "1")
changelog = "%s: If cap= is present, remove it, else add lc=" % template
msg("Page %s %s: Change log = %s" % (index, pagetitle, changelog))
return text, changelog
for index, page in blib.references("Template:" + template, startFrom, upTo):
blib.do_edit(page, index, fix_one_page_tool_place_noun, save=save,
verbose=verbose)
pa = blib.init_argparser("Fix lc vs. cap in tool/place noun etym templates")
params = pa.parse_args()
startFrom, upTo = blib.parse_start_end(params.start, params.end)
fix_tool_place_noun(params.save, params.verbose, startFrom, upTo)
if m.group(2):
tr = "|tr=%s" % m.group(2)
else:
tr = ""
repl = "{{l|ar|%s%s%s}}" % (m.group(1), tr, gender)
msg("Replacing\n%s\nwith\n%s" % (m.group(0), repl))
newtext = text.replace(m.group(0), repl, 1)
if newtext == text:
msg("WARNING: Unable to do replacement")
else:
text = newtext
linkschanged.append(m.group(1))
return text, "incorporated translit/gender into links: %s" % ', '.join(linkschanged)
def correct_link_formatting(save, startFrom, upTo):
for cat in [u"Arabic lemmas", u"Arabic non-lemma forms"]:
for index, page in blib.cat_articles(cat, startFrom, upTo):
blib.do_edit(page, index, correct_one_page_link_formatting, save=save)
pa = blib.init_argparser("Correct formatting of headword templates")
pa.add_argument("-l", "--links", action='store_true',
help="Vocalize links")
params = pa.parse_args()
startFrom, upTo = blib.parse_start_end(params.start, params.end)
if params.links:
correct_link_formatting(params.save, startFrom, upTo)
else:
correct_headword_formatting(params.save, startFrom, upTo)
oldtemps.append(origname)
if nochange:
return None, ""
if oldtemps:
comment = "convert %s -> ru-noun-table" % ", ".join(oldtemps)
else:
comment = None
return text, comment
def rewrite_ru_decl_noun(save, verbose, startFrom, upTo):
for cat in [u"Russian nouns"]:
for page, index in blib.cat_articles(cat, startFrom, upTo):
blib.do_edit(page, index, rewrite_one_page_ru_decl_noun, save=save, verbose=verbose)
def rewrite_ru_decl_adj(save, verbose, startFrom, upTo):
for cat in [u"Russian adjectives"]:
for page, index in blib.cat_articles(cat, startFrom, upTo):
blib.do_edit(page, index, rewrite_one_page_ru_decl_adj, save=save, verbose=verbose)
pa = blib.init_argparser("Rewrite Russian old declension templates")
pa.add_argument("--adjectives", action='store_true',
help="Rewrite old adjective templates")
pa.add_argument("--nouns", action='store_true',
help="Rewrite old noun templates")
params = pa.parse_args()
startFrom, upTo = blib.parse_start_end(params.start, params.end)
if params.adjectives:
rewrite_ru_decl_adj(params.save, params.verbose, startFrom, upTo)
if params.nouns:
rewrite_ru_decl_noun(params.save, params.verbose, startFrom, upTo)
return newtext, changelog
page = pywikibot.Page(site, pagename)
if not page.exists():
msg("Page %s %s: WARNING, something wrong, does not exist" %
(index, pagename))
else:
blib.do_edit(page,
index,
push_one_manual_change,
save=save,
verbose=verbose,
diff=diff)
pa = blib.init_argparser("Push manual changes to Wiktionary")
pa.add_argument(
"--file",
help="File containing templates to change, as output by parse_log_file.py")
pa.add_argument(
"--annotation",
default="manually",
help=
"Annotation in change log message used to indicate source of changes (default 'manually')"
)
params = pa.parse_args()
startFrom, upTo = blib.parse_start_end(params.start, params.end)
push_manual_changes(params.save, params.verbose, params.diff, params.file,
params.annotation.decode('utf-8'), startFrom, upTo)
else:
pagemsg("Original template found, taking no action")
else:
if found_orig_template:
pagemsg("WARNING: Undid removal, but original template %s already present!" %
orig_template)
if len(newtext) - len(text) != len(to_template) - len(from_template):
pagemsg("WARNING: Length mismatch when undoing Greek param removal, may have matched multiple templates: from=%s, to=%s" % (
from_template, to_template))
changelog = "Undid removal of %s=%s in %s" % (removed_param,
param_value, to_template)
pagemsg("Change log = %s" % changelog)
return newtext, changelog
page = pywikibot.Page(site, pagename)
if not page.exists():
msg("Page %s %s: WARNING, something wrong, does not exist" % (
index, pagename))
else:
blib.do_edit(page, index, undo_one_page_greek_removal, save=save,
verbose=verbose)
pa = blib.init_argparser("Undo Greek transliteration removal")
pa.add_argument("--file",
help="File containing templates and removal directives to undo")
params = pa.parse_args()
startFrom, upTo = blib.parse_start_end(params.start, params.end)
undo_greek_removal(params.save, params.verbose, params.file, startFrom, upTo)
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program. If not, see <http://www.gnu.org/licenses/>.
import blib
from blib import getparam, addparam
def rewrite_one_page_ar_plural(page, index, text):
for template in text.filter_templates():
if template.name == "ar-plural":
template.name = "ar-noun-pl"
return text, "rename {{temp|ar-plural}} to {{temp|ar-noun-pl}}"
def rewrite_ar_plural(save, verbose, startFrom, upTo):
for cat in [u"Arabic plurals"]:
for page, index in blib.cat_articles(cat, startFrom, upTo):
blib.do_edit(page, index, rewrite_one_page_ar_plural, save=save, verbose=verbose)
pa = blib.init_argparser("Rewrite ar-plural to ar-noun-pl templates")
params = pa.parse_args()
startFrom, upTo = blib.parse_start_end(params.start, params.end)
rewrite_ar_plural(params.save, params.verbose, startFrom, upTo)
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program. If not, see <http://www.gnu.org/licenses/>.
import blib
from blib import getparam, addparam
def rewrite_one_page_ar_plural(page, index, text):
for template in text.filter_templates():
if template.name == "ar-plural":
template.name = "ar-noun-pl"
return text, "rename {{temp|ar-plural}} to {{temp|ar-noun-pl}}"
def rewrite_ar_plural(save, verbose, startFrom, upTo):
for cat in [u"Arabic plurals"]:
for index, page in blib.cat_articles(cat, startFrom, upTo):
blib.do_edit(page, index, rewrite_one_page_ar_plural, save=save, verbose=verbose)
pa = blib.init_argparser("Rewrite ar-plural to ar-noun-pl templates")
params = pa.parse_args()
startFrom, upTo = blib.parse_start_end(params.start, params.end)
rewrite_ar_plural(params.save, params.verbose, startFrom, upTo)
if num_modhead_changed:
actions.append(u"Changed modN to modheadN")
if num_state_ind_to_ind_def:
actions.append(u"Converted state=ind to state=ind-def for proper noun")
if num_basestate_ind_def:
actions.append(u"Converted state=def|basestate=ind to state=ind-def")
if actions:
changelog = "; ".join(actions)
pagemsg("Changelog = %s" % changelog)
return text, changelog
return text, ""
def rewrite_idafa(save, verbose, startFrom, upTo):
for template in arabic_decl_templates:
for index, page in blib.references("Template:" + template, startFrom,
upTo):
blib.do_edit(page,
index,
rewrite_one_page_idafa,
save=save,
verbose=verbose)
pa = blib.init_argparser(
u"Rewrite ʾidāfa params with idafa= param, and related changes")
params = pa.parse_args()
startFrom, upTo = blib.parse_start_end(params.start, params.end)
rewrite_idafa(params.save, params.verbose, startFrom, upTo)
yield index, page, None
for index, page, totitle in yield_pages():
pagetitle = unicode(page.title())
if filter_pages and not re.search(filter_pages, pagetitle):
msg("Skipping %s because doesn't match --filter-pages regex %s" %
(pagetitle, filter_pages))
elif not page.exists():
msg("Skipping %s because page doesn't exist" % pagetitle)
else:
if verbose:
msg("Processing %s" % pagetitle)
rename_one_page(page, totitle, index)
pa = blib.init_argparser("Rename pages")
pa.add_argument("-f",
"--from",
help="From regex, can be specified multiple times",
metavar="FROM",
dest="from_",
action="append")
pa.add_argument("-t",
"--to",
help="To regex, can be specified multiple times",
action="append")
pa.add_argument(
"-r",
"--references",
"--refs",
help="Do pages with references to these pages (comma-separated)")
def fix_one_page_tool_place_noun(page, index, text):
pagetitle = page.title()
for t in text.filter_templates():
if t.name == template:
if getparam(t, "cap"):
msg("Page %s %s: Template %s: Remove cap=" %
(index, pagetitle, template))
t.remove("cap")
else:
msg("Page %s %s: Template %s: Add lc=1" %
(index, pagetitle, template))
addparam(t, "lc", "1")
changelog = "%s: If cap= is present, remove it, else add lc=" % template
msg("Page %s %s: Change log = %s" % (index, pagetitle, changelog))
return text, changelog
for index, page in blib.references("Template:" + template, startFrom,
upTo):
blib.do_edit(page,
index,
fix_one_page_tool_place_noun,
save=save,
verbose=verbose)
pa = blib.init_argparser("Fix lc vs. cap in tool/place noun etym templates")
params = pa.parse_args()
startFrom, upTo = blib.parse_start_end(params.start, params.end)
fix_tool_place_noun(params.save, params.verbose, startFrom, upTo)
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program. If not, see <http://www.gnu.org/licenses/>.
import blib
from blib import getparam, addparam
def rewrite_one_page_ar_nisba(page, index, text):
for template in text.filter_templates():
if template.name == "ar-nisba":
if template.has("head") and not template.has(1):
head = unicode(template.get("head").value)
template.remove("head")
addparam(template, "1", head, before=template.params[0].name if len(template.params) > 0 else None)
if template.has("plhead"):
blib.msg("%s has plhead=" % page.title())
return text, "ar-nisba: head= -> 1="
def rewrite_ar_nisba(save, verbose, startFrom, upTo):
for index, page in blib.references("Template:ar-nisba", startFrom, upTo):
blib.do_edit(page, index, rewrite_one_page_ar_nisba, save=save, verbose=verbose)
pa = blib.init_argparser("Rewrite ar-nisba, changing head= to 1=")
params = pa.parse_args()
startFrom, upTo = blib.parse_start_end(params.start, params.end)
rewrite_ar_nisba(params.save, params.verbose, startFrom, upTo)
ruparam, trparam):
def pagemsg(text):
msg("Page %s %s: %s" % (index, pagetitle, text))
def output_line(directive):
pagemsg("%s: %s" % (directive, unicode(template)))
result = process_template(pagetitle, index, template, ruparam, trparam,
output_line, find_accents, verbose)
if index % 100 == 0:
output_stats(pagemsg)
return result
blib.process_links(save, verbose, "ru", "Russian", cattype, startFrom,
upTo, check_template_for_missing_accent,
join_actions=join_changelog_notes, split_templates=None)
pa = blib.init_argparser("Find Russian terms needing accents")
pa.add_argument("--cattype", default="vocab",
help="Categories to examine ('vocab', 'borrowed', 'translation')")
pa.add_argument("--file",
help="File containing output from parse_log_file.py")
pa.add_argument("--semi-verbose", action="store_true",
help="More info but not as much as --verbose")
pa.add_argument("--find-accents", action="store_true",
help="Look up the accents in existing pages")
pa.add_argument("--no-cache", action="store_true",
help="Disable caching head lookup results")
params = pa.parse_args()
semi_verbose = params.semi_verbose or params.verbose
global_disable_cache = params.no_cache
startFrom, upTo = blib.parse_start_end(params.start, params.end)
# Vocalize link-like templates on pages from STARTFROM to (but not including)
# UPTO, either page names or 0-based integers. Save changes if SAVE is true.
# Show exact changes if VERBOSE is true. CATTYPE should be 'vocab', 'borrowed'
# or 'translation', indicating which categories to examine.
def vocalize_links(save, verbose, cattype, startFrom, upTo):
def process_param(pagetitle, index, template, param, paramtr):
result = vocalize_param(pagetitle, index, template, param, paramtr)
if isinstance(result, basestring):
result = ["%s (%s)" % (result, template.name)]
return result
def join_actions(actions):
return "vocalize links: %s" % '; '.join(actions)
return blib.process_links(save, verbose, "ar", "Arabic", cattype,
startFrom, upTo, process_param, join_actions)
pa = blib.init_argparser("Correct vocalization and translit")
pa.add_argument("-l", "--links", action='store_true',
help="Vocalize links")
pa.add_argument("--cattype", default="borrowed",
help="Categories to examine ('vocab', 'borrowed', 'translation')")
params = pa.parse_args()
startFrom, upTo = blib.parse_start_end(params.start, params.end)
if params.links:
vocalize_links(params.save, params.verbose, params.cattype, startFrom, upTo)
else:
vocalize_headwords(params.save, params.verbose, startFrom, upTo)
for vn in vns:
no_i3rab_vns.append(remove_i3rab(pagename, index, verbid, vn))
newvn = ",".join(no_i3rab_vns)
if uncertain:
newvn += "?"
if newvn != vnvalue:
msg("Page %s %s: Verb %s, replacing %s with %s" % (
index, pagename, verbid, vnvalue, newvn))
addparam(template, "vn", newvn)
verbids.append(verbid)
return text, "Remove i3rab from verbal nouns for verb(s) %s" % (
', '.join(verbids))
for page, index in blib.cat_articles("Arabic verbs", startFrom, upTo):
blib.do_edit(page, index, do_one_page_verb, save=save, verbose=verbose)
pa = blib.init_argparser("Remove i3rab")
pa.add_argument("--verb", action='store_true',
help="Do verbal nouns in verbs")
pa.add_argument("--noun", action='store_true',
help="Do arguments in nouns")
params = pa.parse_args()
startFrom, upTo = blib.parse_start_end(params.start, params.end)
if params.noun:
do_nouns(["noun", "adjective"],
["ar-noun", "ar-coll-noun", "ar-sing-noun", "ar-nisba", "ar-noun-nisba",
"ar-adj", "ar-numeral"],
params.save, startFrom, upTo)
if params.verb:
do_verbs(params.save, startFrom, upTo)
include_tempname_in_changelog=True)
if getparam(template, "sc") == "Arab":
msg("Page %s %s: %s.%s: Removing sc=Arab" % (index, pagetitle,
template.name, "sc"))
oldtempl = "%s" % unicode(template)
template.remove("sc")
msg("Page %s %s: Replaced %s with %s" %
(index, pagetitle, oldtempl, unicode(template)))
newresult = ["remove %s.sc=Arab" % template.name]
if isinstance(result, list):
result = result + newresult
else:
result = newresult
return result
return blib.process_links(save, verbose, "ar", "Arabic", cattype,
startFrom, upTo, do_process_param, sort_group_changelogs)
pa = blib.init_argparser("Remove redundant translit")
pa.add_argument("-l", "--links", action='store_true',
help="Vocalize links")
pa.add_argument("--cattype", default="borrowed",
help="Categories to examine ('vocab', 'borrowed', 'translation')")
params = pa.parse_args()
startFrom, upTo = blib.parse_start_end(params.start, params.end)
if params.links:
process_links(params.save, params.verbose, params.cattype, startFrom, upTo)
else:
process_headwords(params.save, params.verbose, startFrom, upTo)
pages = ((pywikibot.Page(blib.site, page), index) for page, index in blib.iter_pages(lines, startFrom, upTo))
elif refs:
pages = blib.references(refs, startFrom, upTo, includelinks=True)
else:
pages = blib.cat_articles(cat, startFrom, upTo)
for page, index in pages:
pagetitle = unicode(page.title())
if filter_pages and not re.search(filter_pages, pagetitle):
blib.msg("Skipping %s because doesn't match --filter-pages regex %s" %
(pagetitle, filter_pages))
else:
if verbose:
blib.msg("Processing %s" % pagetitle)
blib.do_edit(page, index, rewrite_one_page, save=save, verbose=verbose)
pa = blib.init_argparser("Search and replace on pages")
pa.add_argument("-f", "--from", help="From regex, can be specified multiple times",
metavar="FROM", dest="from_", required=True, action="append")
pa.add_argument("-t", "--to", help="To regex, can be specified multiple times",
required=True, action="append")
pa.add_argument("-r", "--references", "--refs",
help="Do pages with references to this page")
pa.add_argument("-c", "--category", "--cat",
help="Do pages in this category")
pa.add_argument("--comment", help="Specify the change comment to use")
pa.add_argument('--filter-pages', help="Regex to use to filter page names.")
pa.add_argument('--pages', help="List of pages to fix, comma-separated.")
pa.add_argument('--pagefile', help="File containing pages to fix.")
pa.add_argument('--pagetitle', help="Value to substitute page title with.")
params = pa.parse_args()
startFrom, upTo = blib.parse_start_end(params.start, params.end)
# Check for changed text and save if so.
notestext = '; '.join(notes)
if notestext:
if comment:
comment += " (%s)" % notestext
else:
comment = notestext
if page.text != existing_text:
if save:
pagemsg("Saving with comment = %s" % comment)
blib.safe_page_save(page, comment, errandpagemsg)
else:
pagemsg("Would save with comment = %s" % comment)
pa = blib.init_argparser("Save Russian numbers to Wiktionary")
pa.add_argument("--offline",
help="Operate offline, outputting text of new pages",
action="store_true")
pa.add_argument(
"--overwrite-page",
action="store_true",
help=u"""If specified, overwrite the entire existing page of inflections.
Won't do this if it finds "Etymology N", unless --overwrite-etymologies is
given. WARNING: Be careful!""")
pa.add_argument(
"--overwrite-etymologies",
action="store_true",
help=u"""If specified and --overwrite-page, overwrite the entire existing
page of inflections even if "Etymology N". WARNING: Be careful!""")
pa.add_argument(
addparam(t, "tr", tr)
if f:
addparam(t, "f", f)
if ftr:
addparam(t, "ftr", ftr)
if pl:
addparam(t, "pl", pl)
if pltr:
addparam(t, "pltr", pltr)
if sort:
addparam(t, "sort", sort)
temps_changed.append("arz-adj")
return text, "rewrite %s to new style" % ", ".join(temps_changed)
def rewrite_arz_headword(save, verbose, startFrom, upTo):
for cat in [u"Egyptian Arabic adjectives", "Egyptian Arabic nouns"]:
for index, page in blib.cat_articles(cat, startFrom, upTo):
blib.do_edit(page,
index,
rewrite_one_page_arz_headword,
save=save,
verbose=verbose)
pa = blib.init_argparser("Rewrite Egyptian Arabic headword templates")
params = pa.parse_args()
startFrom, upTo = blib.parse_start_end(params.start, params.end)
rewrite_arz_headword(params.save, params.verbose, startFrom, upTo)
def vocalize_links(save, verbose, cattype, startFrom, upTo):
def process_param(pagetitle, index, pagetext, template, tlang, param,
paramtr):
result = vocalize_param(pagetitle, index, template, param, paramtr)
if isinstance(result, basestring):
result = ["%s (%s)" % (result, template.name)]
return result
def join_actions(actions):
return "vocalize links: %s" % '; '.join(actions)
return blib.process_links(save, verbose, "ar", "Arabic", cattype,
startFrom, upTo, process_param, join_actions)
pa = blib.init_argparser("Correct vocalization and translit")
pa.add_argument("-l", "--links", action='store_true', help="Vocalize links")
pa.add_argument(
"--cattype",
default="borrowed",
help="Categories to examine ('vocab', 'borrowed', 'translation')")
params = pa.parse_args()
startFrom, upTo = blib.parse_start_end(params.start, params.end)
if params.links:
vocalize_links(params.save, params.verbose, params.cattype, startFrom,
upTo)
else:
vocalize_headwords(params.save, params.verbose, startFrom, upTo)
include_tempname_in_changelog=True)
if getparam(template, "sc") == "Arab":
msg("Page %s %s: %s.%s: Removing sc=Arab" % (index, pagetitle,
template.name, "sc"))
oldtempl = "%s" % unicode(template)
template.remove("sc")
msg("Page %s %s: Replaced %s with %s" %
(index, pagetitle, oldtempl, unicode(template)))
newresult = ["remove %s.sc=Arab" % template.name]
if isinstance(result, list):
result = result + newresult
else:
result = newresult
return result
return blib.process_links(save, verbose, "ar", "Arabic", cattype,
startFrom, upTo, do_process_param, sort_group_changelogs)
pa = blib.init_argparser("Remove redundant translit")
pa.add_argument("-l", "--links", action='store_true',
help="Vocalize links")
pa.add_argument("--cattype", default="borrowed",
help="Categories to examine ('vocab', 'borrowed', 'translation')")
params = pa.parse_args()
startFrom, upTo = blib.parse_start_end(params.start, params.end)
if params.links:
process_links(params.save, params.verbose, params.cattype, startFrom, upTo)
else:
process_headwords(params.save, params.verbose, startFrom, upTo)
yield page.title()
if params.ignore_lemma_non_lemma:
pages_to_ignore = set(yield_lemma_non_lemma_page_titles())
else:
pages_to_ignore = set()
for category in yield_cats():
msg("Processing category %s ..." % category)
errmsg("Processing category %s ..." % category)
for index, page in blib.cat_articles(category, startFrom, upTo):
if page.title() not in pages_to_ignore:
blib.do_edit(page, index, remove_translit_one_page, save=params.save,
verbose=params.verbose)
pa = blib.init_argparser("Remove translit, sc= from hy, xcl, ka, el, grc templates")
pa.add_argument("--langs", default="all",
help="Languages to do, a comma-separated list or 'all'")
pa.add_argument("--cattype", default="all",
help="""Categories to examine ('all' or comma-separated list of
'translit', 'lemma', 'non-lemma'; default 'all')""")
pa.add_argument("--ignore-lemma-non-lemma", action="store_true",
help="""Ignore lemma and non-lemma pages (useful with '--cattype translit').""")
pa.add_argument("--do-head", action="store_true",
help="""Remove tr= in {{head|..}}""")
params = pa.parse_args()
startFrom, upTo = blib.parse_start_end(params.start, params.end)
remove_translit(params, startFrom, upTo)
msg("Templates processed:")
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program. If not, see <http://www.gnu.org/licenses/>.
import re, codecs
import blib
import grc_translit
from canon_foreign import canon_links
pa = blib.init_argparser("Canonicalize Greek and translit")
pa.add_argument(
"--cattype",
default="borrowed",
help="""Categories to examine ('vocab', 'borrowed', 'translation',
'links', 'pagetext', 'pages' or comma-separated list)""")
pa.add_argument(
"--page-file",
help="""File containing "pages" to process when --cattype pagetext,
or list of pages when --cattype pages""")
params = pa.parse_args()
startFrom, upTo = blib.parse_start_end(params.start, params.end)
pages_to_do = []
if params.page_file:
for line in codecs.open(params.page_file, "r", encoding="utf-8"):
head = reorder_shadda(getparam(t, "1"))
if t.name.startswith("ar-decl-"):
param = "pl"
pl = getparam(t, param)
i = 2
while pl:
if pl == "smp":
if head.endswith(TAM):
msg("Page %s %s: WARNING: Found %s=smp with feminine ending head %s in %s: not changing" % (
index, pagetitle, param, head, t.name))
else:
msg("Page %s %s: Changing %s=smp to %s=sp in %s" % (
index, pagetitle, param, param, t.name))
addparam(t, param, "sp")
param = "pl%s" % i
pl = getparam(t, param)
i += 1
changelog = "Change pl=smp to pl=sp"
msg("Page %s %s: Change log = %s" % (index, pagetitle, changelog))
return text, changelog
for page, index in blib.references("Template:" + template, startFrom, upTo):
blib.do_edit(page, index, fix_one_page_smp, save=save,
verbose=verbose)
pa = blib.init_argparser("Change |pl=smp to |pl=sp in declension templates")
params = pa.parse_args()
startFrom, upTo = blib.parse_start_end(params.start, params.end)
fix_smp(params.save, params.verbose, startFrom, upTo)
while pl:
if pl == "smp":
if head.endswith(TAM):
msg("Page %s %s: WARNING: Found %s=smp with feminine ending head %s in %s: not changing"
% (index, pagetitle, param, head, t.name))
else:
msg("Page %s %s: Changing %s=smp to %s=sp in %s"
% (index, pagetitle, param, param, t.name))
addparam(t, param, "sp")
param = "pl%s" % i
pl = getparam(t, param)
i += 1
changelog = "Change pl=smp to pl=sp"
msg("Page %s %s: Change log = %s" % (index, pagetitle, changelog))
return text, changelog
for index, page in blib.references("Template:" + template, startFrom,
upTo):
blib.do_edit(page,
index,
fix_one_page_smp,
save=save,
verbose=verbose)
pa = blib.init_argparser("Change |pl=smp to |pl=sp in declension templates")
params = pa.parse_args()
startFrom, upTo = blib.parse_start_end(params.start, params.end)
fix_smp(params.save, params.verbose, startFrom, upTo)
index,
rewrite_one_page_ru_decl_noun,
save=save,
verbose=verbose)
def rewrite_ru_decl_adj(save, verbose, startFrom, upTo):
for cat in [u"Russian adjectives"]:
for index, page in blib.cat_articles(cat, startFrom, upTo):
blib.do_edit(page,
index,
rewrite_one_page_ru_decl_adj,
save=save,
verbose=verbose)
pa = blib.init_argparser("Rewrite Russian old declension templates")
pa.add_argument("--adjectives",
action='store_true',
help="Rewrite old adjective templates")
pa.add_argument("--nouns",
action='store_true',
help="Rewrite old noun templates")
params = pa.parse_args()
startFrom, upTo = blib.parse_start_end(params.start, params.end)
if params.adjectives:
rewrite_ru_decl_adj(params.save, params.verbose, startFrom, upTo)
if params.nouns:
rewrite_ru_decl_noun(params.save, params.verbose, startFrom, upTo)
pagemsg("Replacing [[%s]] with [[%s]]" % (pagetext, newtext))
else:
pagemsg("Text has changed")
pagetext = newtext
# Construct and output comment.
notestext = '; '.join(notes)
if notestext:
if comment:
comment += " (%s)" % notestext
else:
comment = notestext
assert(comment)
pagemsg("comment = %s" % comment, simple = True)
return pagetext, comment
def split_etymologies(save, verbose, startFrom, upTo):
def split_page_etymologies(page, index, pagetext):
return split_one_page_etymologies(page, index, pagetext, verbose)
for index, page in blib.cat_articles("Arabic lemmas", startFrom, upTo):
blib.do_edit(page, index, split_page_etymologies, save=save,
verbose=verbose)
pa = blib.init_argparser("Split etymology sections")
params = pa.parse_args()
startFrom, upTo = blib.parse_start_end(params.start, params.end)
split_etymologies(params.save, True, # params.verbose
startFrom, upTo)
msg("Replacing %s with %s" % (origtemp, newtemp))
if re.match("^[1I](-|$)", form):
actions_taken.append("form=%s (%s/%s)" % (form,
getparam(template, str(1+int(formarg))),
getparam(template, str(2+int(formarg)))))
else:
actions_taken.append("form=%s" % form)
changelog = "%s: canonicalize form (%s=) to Roman numerals: %s" % (
tempname, formarg, '; '.join(actions_taken))
if len(actions_taken) > 0:
msg("Change log = %s" % changelog)
return text, changelog
for page, index in blib.references("Template:%s" % tempname, startFrom, upTo):
blib.do_edit(page, index, canonicalize_one_page_verb_form, save=save)
pa = blib.init_argparser("Rewrite form= to 1= in verb headword templates")
pa.add_argument("--headword", action='store_true',
help="Rewrite form= to 1= in ar-verb and canonicalize")
pa.add_argument("--canonicalize", action='store_true',
help="Canonicalize form in Arabic verb templates other than ar-verb")
params = pa.parse_args()
startFrom, upTo = blib.parse_start_end(params.start, params.end)
if params.headword:
rewrite_verb_headword(params.save, startFrom, upTo)
if params.canonicalize:
canonicalize_verb_form(params.save, startFrom, upTo, "ar-conj", "1")
canonicalize_verb_form(params.save, startFrom, upTo, "ar-past3sm", "1")
canonicalize_verb_form(params.save, startFrom, upTo, "ar-verb-part", "2")
if ratio == int(ratio):
pagemsg("WARNING: Replaced %s occurrences of curr=%s with repl=%s"
% (int(ratio), curr_template, repl_template))
else:
pagemsg("WARNING: Something wrong, length mismatch during replacement: Expected length change=%s, actual=%s, ratio=%.2f, curr=%s, repl=%s"
% (repl_curr_diff, newtext_text_diff, ratio, curr_template,
repl_template))
changelog = "Replaced %s with %s (%s)" % (curr_template, repl_template,
annotation)
pagemsg("Change log = %s" % changelog)
return newtext, changelog
page = pywikibot.Page(site, pagename)
if not page.exists():
msg("Page %s %s: WARNING, something wrong, does not exist" % (
index, pagename))
else:
blib.do_edit(page, index, push_one_manual_change, save=save,
verbose=verbose)
pa = blib.init_argparser("Push manual changes to Wiktionary")
pa.add_argument("--file",
help="File containing templates to change, as output by parse_log_file.py")
pa.add_argument("--annotation", default="manually",
help="Annotation in change log message used to indicate source of changes (default 'manually')")
params = pa.parse_args()
startFrom, upTo = blib.parse_start_end(params.start, params.end)
push_manual_changes(params.save, params.verbose, params.file, params.annotation, startFrom, upTo)