def delete_page(page, comment):
for i in range(11):
try:
page.delete(comment)
return
except APIError as e:
if i == 10:
raise e
errandmsg("APIError, try #%s: %s" % (i + 1, e))
def process_page(page, index, parsed):
pagetitle = unicode(page.title())
def pagemsg(txt):
msg("Page %s %s: %s" % (index, pagetitle, txt))
pagemsg("Processing")
notes = []
for t in parsed.filter_templates():
origt = unicode(t)
tn = tname(t)
if tn in templates_to_rename:
template_specs = templates_to_rename[tn]
new_name, new_params = template_specs[0], template_specs[1:]
main_entry_param = "adj" if new_name == "bg-adj form of" else "noun"
blib.set_template_name(t, new_name)
# Fetch all params.
params = []
old_1 = getparam(t, "1")
for param in t.params:
pname = unicode(param.name)
if pname.strip() in ["1", "lang", "sc"]:
continue
if pname.strip() in ["2", "3", "4"]:
errandmsg("WARNING: Found %s= in %s" %
(pname.strip(), origt))
params.append((pname, param.value, param.showkey))
# Erase all params.
del t.params[:]
# Put back basic params
for param_index, paramval in enumerate(new_params):
t.add(str(param_index + 1), paramval)
if not old_1:
errandmsg("WARNING: No 1= in %s" % origt)
else:
t.add(main_entry_param, old_1)
# Put remaining parameters in order.
for name, value, showkey in params:
t.add(name, value, showkey=showkey, preserve_spacing=False)
notes.append(
"rename {{%s}} to {{%s|%s|%s={{{1}}}}}" %
(tn, new_name, "|".join(new_params), main_entry_param))
if unicode(t) != origt:
pagemsg("Replaced <%s> with <%s>" % (origt, unicode(t)))
return unicode(parsed), notes
def errandpagemsg(txt):
errandmsg("Page %s %s: %s" % (index, pagetitle, txt))
def do_process_page(page, index, parsed=None):
pagetitle = unicode(page.title())
def pagemsg(txt):
msg("Page %s %s: %s" % (index, pagetitle, txt))
pagetext = blib.safe_page_text(page, pagemsg)
return process_text_on_page_for_full_conj(index, pagetitle, pagetext, verbs)
page = pywikibot.Page(site, verb)
blib.do_edit(page, lineno, do_process_page, save=args.save, verbose=args.verbose, diff=args.diff)
elif args.mode == "generate":
verbs = {}
for line in codecs.open(args.direcfile, "r", encoding="utf-8"):
line = line.strip()
if line.startswith("#"):
continue
if " " not in line:
errandmsg("WARNING: No space in line: %s" % line)
continue
verb, spec = line.split(" ", 1)
verbs[verb] = spec
def do_process_page(page, index):
return process_page_for_generate(page, index, verbs)
blib.do_pagefile_cats_refs(args, start, end, do_process_page)
else:
lineno = 0
for line in codecs.open(args.direcfile, "r", encoding="utf-8"):
lineno += 1
line = line.strip()
if line.startswith("#"):
continue
if " " not in line:
errandmsg("WARNING: No space in line: %s" % line)
def process_page(page, index, parsed, move_dot, rename):
pagetitle = unicode(page.title())
def pagemsg(txt):
msg("Page %s %s: %s" % (index, pagetitle, txt))
pagemsg("Processing")
notes = []
text = unicode(page.text)
if ":" in pagetitle and not re.search(
"^(Citations|Appendix|Reconstruction|Transwiki|Talk|Wiktionary|[A-Za-z]+ talk):", pagetitle):
pagemsg("WARNING: Colon in page title and not a recognized namespace to include, skipping page")
return None, None
if move_dot:
templates_to_replace = []
for t in parsed.filter_templates():
tn = tname(t)
if tn in all_he_form_of_templates:
dot = getparam(t, ".")
if dot:
origt = unicode(t)
rmparam(t, ".")
newt = unicode(t) + dot
templates_to_replace.append((origt, newt))
for curr_template, repl_template in templates_to_replace:
found_curr_template = curr_template in text
if not found_curr_template:
pagemsg("WARNING: Unable to locate template: %s" % curr_template)
continue
found_repl_template = repl_template in text
if found_repl_template:
pagemsg("WARNING: Already found template with period: %s" % repl_template)
continue
newtext = text.replace(curr_template, repl_template)
newtext_text_diff = len(newtext) - len(text)
repl_curr_diff = len(repl_template) - len(curr_template)
ratio = float(newtext_text_diff) / repl_curr_diff
if ratio == int(ratio):
if int(ratio) > 1:
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))
text = newtext
notes.append("move .= outside of {{he-*}} template")
if rename:
parsed = blib.parse_text(text)
for t in parsed.filter_templates():
origt = unicode(t)
tn = tname(t)
if tn in all_he_form_of_template_map:
newname, add_nocap = all_he_form_of_template_map[tn]
add_nocap_msg = "|nocap=1" if add_nocap else ""
newspecs = None
if "|" in newname:
newname, newspecs = newname.split("|")
blib.set_template_name(t, newname)
# Fetch all params.
params = []
old_1 = getparam(t, "1")
for param in t.params:
pname = unicode(param.name)
if pname.strip() in ["1", "lang", "sc"]:
continue
if pname.strip() in (
newname == "he-infinitive of" and ["3", "4"] or ["2", "3", "4"]
):
errandmsg("WARNING: Found %s= in %s" % (pname.strip(), origt))
params.append((pname, param.value, param.showkey))
# Erase all params.
del t.params[:]
# Put back basic params
t.add("1", old_1)
if newname == "he-verb form of":
assert newspecs
t.add("2", newspecs)
notes.append("rename {{%s}} to {{%s|{{{1}}}|%s%s}}" %
(tn, newname, newspecs, add_nocap_msg))
elif newname == "he-noun form of" and newspecs:
newparam, newval = newspecs.split("=")
t.add(newparam, newval)
notes.append("rename {{%s}} to {{%s|{{{1}}}|%s=%s%s}}" %
(tn, newname, newparam, newval, add_nocap_msg))
else:
notes.append("rename {{%s}} to {{%s%s}}" % (tn, newname, add_nocap_msg))
# Put remaining parameters in order.
for name, value, showkey in params:
# More hacking for 'he-form of sing cons': p -> pp, g -> pg, n -> pn
if newname == "he-noun form of" and newspecs:
if name in ["p", "g", "n"]:
name = "p" + name
t.add(name, value, showkey=showkey, preserve_spacing=False)
# Finally add nocap=1 if requested.
if add_nocap:
t.add("nocap", "1")
if unicode(t) != origt:
pagemsg("Replaced <%s> with <%s>" % (origt, unicode(t)))
text = unicode(parsed)
return text, notes
def errandpagemsg(txt):
errandmsg("Page %s %s: form %s %s: %s" %
(index, lemma, formind, formval, txt))
def errandpagemsg(txt):
errandmsg("Page %s %s: %s" % (index, lemma, txt))
return text, notes
parser = blib.create_argparser(
"Push manual {{fr-IPA}} replacements for {{IPA|fr}}")
parser.add_argument("--direcfile", help="File of directives", required=True)
args = parser.parse_args()
start, end = blib.parse_start_end(args.start, args.end)
for index, line in blib.iter_items(
codecs.open(args.direcfile, "r", encoding="utf-8"), start, end):
line = line.strip()
m = re.search(
r"^(.*?)\|Page [0-9]+ (.*?): WARNING: Can't replace (\{\{IPA\|fr\|.*?\}\}) with (\{\{.*?\}\}) because auto-generated pron .*$",
line)
if not m:
errandmsg("Unrecognized line: %s" % line)
continue
respelling, page, orig_template, repl_template = m.groups()
def do_process_page(page, index, parsed):
return process_page(page, index, line, respelling, orig_template,
repl_template, args)
blib.do_edit(pywikibot.Page(site, page),
index,
do_process_page,
save=args.save,
verbose=args.verbose,
diff=args.diff)
parser = blib.create_argparser(
"Clean up various form-of templates needing text moved outside of template into separate template"
)
parser.add_argument('--move-dot',
help="Move .= outside of template",
action="store_true")
parser.add_argument("--pagefile", help="List of pages to process.")
args = parser.parse_args()
start, end = blib.parse_start_end(args.start, args.end)
init_all_templates(args.move_dot)
for template in all_templates:
errandmsg("Processing references to Template:%s" % template)
for i, page in blib.references("Template:%s" % template, start, end):
blib.do_edit(page,
i,
process_page,
save=args.save,
verbose=args.verbose)
if args.pagefile:
pages = [x.rstrip('\n') for x in codecs.open(args.pagefile, "r", "utf-8")]
for i, page in blib.iter_items(pages, start, end):
blib.do_edit(pywikibot.Page(site, page),
i,
process_page_2,
save=args.save,
verbose=args.verbose)
def errandpagemsg(txt):
errandmsg("Page %s %s: %s" % (nextpage, tempname, txt))
blib.safe_page_save(page, comment, errandpagemsg)
else:
pagemsg("Would save with comment = %s" % comment)
while True:
try:
line = next(lines)
except StopIteration:
break
if in_multiline and re.search("^-+ end text -+$", line):
in_multiline = False
save_template_doc(tempname, "".join(templines), args.save)
elif in_multiline:
if line.rstrip('\n').endswith(':'):
errandmsg("WARNING: Possible missing ----- end text -----: %s" %
line.rstrip('\n'))
templines.append(line)
else:
line = line.rstrip('\n')
if line.endswith(':'):
tempname = line[:-1]
in_multiline = True
templines = []
else:
m = re.search('^(.*?):(.*)$', line)
assert m
tempname = m.group(1)
tempparams = m.group(2).split(",")
params = {}
for tp in tempparams:
if tp in [
doc_comment = "Delete documentation page of " + re.sub(
"^([Dd]elete|[Rr]emove) ", "", comment)
def delete_page(page, comment):
for i in range(11):
try:
page.delete(comment)
return
except APIError as e:
if i == 10:
raise e
errandmsg("APIError, try #%s: %s" % (i + 1, e))
for i, pagename in blib.iter_items(pages_to_delete, start, end):
page = pywikibot.Page(site, pagename)
if page.exists():
msg("Deleting %s (comment=%s)" % (page.title(), comment))
delete_page(page,
'%s (content was "%s")' % (comment, unicode(page.text)))
errandmsg("Page [[%s]] deleted" % page.title())
if args.delete_docs:
doc_page = pywikibot.Page(site, "%s/documentation" % pagename)
if doc_page.exists():
msg("Deleting %s (comment=%s)" % (doc_page.title(), doc_comment))
delete_page(
doc_page, '%s (content was "%s")' %
(doc_comment, unicode(doc_page.text)))
errandmsg("Page [[%s]] deleted" % doc_page.title())