def process_page(page, index, verbose):
pagetitle = unicode(page.title())
def pagemsg(txt):
msg("Page %s %s: %s" % (index, pagetitle, txt))
pagemsg("WARNING: Script no longer applies and would need fixing up")
return
pagemsg("Processing")
text = unicode(page.text)
parsed = blib.parse(page)
notes = []
for t in parsed.filter_templates():
origt = unicode(t)
if unicode(t.name) in ["ru-conj-5c", "ru-conj-6b"]:
past_f = getparam(t, "4")
if past_f:
t.add("past_f", past_f, before="4")
rmparam(t, "4")
notes.append("Replace 4= with past_f=")
newt = unicode(t)
if origt != newt:
pagemsg("Replaced %s with %s" % (origt, newt))
return unicode(parsed), notes
def snarf_adj_accents():
for index, page in blib.cat_articles("Bulgarian adjectives"):
pagetitle = unicode(page.title())
def pagemsg(txt):
msg("Page %s %s: %s" % (index, pagetitle, txt))
parsed = blib.parse(page)
for t in parsed.filter_templates():
if tname(t) == "bg-adj":
adj = getparam(t, "1")
if not adj:
pagemsg("WARNING: Missing headword in adj: %s" %
unicode(t))
continue
if bglib.needs_accents(adj):
pagemsg("WARNING: Adjective %s missing an accent: %s" %
(adj, unicode(t)))
continue
unaccented_adj = bglib.remove_accents(adj)
if unaccented_adj in adjs_to_accents and adjs_to_accents[
unaccented_adj] != adj:
pagemsg(
"WARNING: Two different accents possible for %s: %s and %s: %s"
% (unaccented_adj, adjs_to_accents[unaccented_adj],
adj, unicode(t)))
adjs_to_accents[unaccented_adj] = adj
def process_page(page, index, parsed):
pagetitle = unicode(page.title())
def pagemsg(txt):
msg("Page %s %s: %s" % (index, pagetitle, txt))
pagemsg("Processing")
text = unicode(page.text)
parsed = blib.parse(page)
notes = []
for t in parsed.filter_templates():
if unicode(t.name) == "ru-ux":
origt = unicode(t)
if t.has("adj"):
pagemsg("Removing adj=")
notes.append("remove adj= from ru-ux")
rmparam(t, "adj")
if t.has("shto"):
pagemsg("Removing shto=")
notes.append("remove shto= from ru-ux")
rmparam(t, "shto")
newt = unicode(t)
if origt != newt:
pagemsg("Replaced %s with %s" % (origt, newt))
return unicode(parsed), notes
def process_page(page, index, parsed):
pagetitle = unicode(page.title())
def pagemsg(txt):
msg("Page %s %s: %s" % (index, pagetitle, txt))
pagemsg("WARNING: Script no longer applies and would need fixing up")
return
pagemsg("Processing")
text = unicode(page.text)
parsed = blib.parse(page)
notes = []
for t in parsed.filter_templates():
origt = unicode(t)
if unicode(t.name) in ["ru-conj-4a"]:
shch = getparam(t, "4")
if shch == u"щ":
t.add("3", getparam(t, "3") + shch)
rmparam(t, "4")
notes.append(u"move param 4 (щ) to param 3")
elif shch:
pagemsg("WARNING: Strange value %s for param 4" % shch)
newt = unicode(t)
if origt != newt:
pagemsg("Replaced %s with %s" % (origt, newt))
return unicode(parsed), notes
def process_page(page, index, parsed):
pagetitle = unicode(page.title())
def pagemsg(txt):
msg("Page %s %s: %s" % (index, pagetitle, txt))
pagemsg("Processing")
text = unicode(page.text)
parsed = blib.parse(page)
notes = []
for t in parsed.filter_templates():
origt = unicode(t)
if unicode(t.name) in [
"quote-book", "quote-hansard", "quote-journal",
"quote-newsgroup", "quote-song", "quote-us-patent",
"quote-video", "quote-web", "quote-wikipedia"
] and getparam(t, "lang") == "ru":
passage = getparam(t, "passage")
m = re.search(r"^\{\{lang\|ru\|(.*)\}\}$", passage)
if m:
t.add("passage", m.group(1))
notes.append("remove {{lang|ru|...}} from passage= in quote-*")
newt = unicode(t)
if origt != newt:
pagemsg("Replaced %s with %s" % (origt, newt))
return unicode(parsed), notes
def process_page(page, index, parsed):
pagetitle = unicode(page.title())
def pagemsg(txt):
msg("Page %s %s: %s" % (index, pagetitle, txt))
pagemsg("Processing")
text = unicode(page.text)
notes = []
parsed = blib.parse(page)
for t in parsed.filter_templates():
origt = unicode(t)
if unicode(t.name) in ["ru-conj", "ru-conj-old"]:
verbtype = getparam(t, "2")
if verbtype in [
"pf", "pf-intr", "pf-refl", "pf-impers", "pf-intr-impers",
"pf-refl-impers", "impf", "impf-intr", "impf-refl",
"impf-impers", "impf-intr-impers", "impf-refl-impers"
]:
conjtype = getparam(t, "1")
t.add("2", conjtype)
t.add("1", verbtype)
notes.append("move verb type from arg 2 to arg 1")
newt = unicode(t)
if origt != newt:
pagemsg("Replaced %s with %s" % (origt, newt))
return unicode(parsed), notes
def process_page(index, page, save, verbose):
pagetitle = unicode(page.title())
def pagemsg(txt):
msg("Page %s %s: %s" % (index, pagetitle, txt))
pagemsg("Processing")
text = unicode(page.text)
parsed = blib.parse(page)
found_inflection_of = False
found_head_verb_form = False
for t in parsed.filter_templates():
if unicode(t.name) in ["inflection of"]:
found_inflection_of = True
if unicode(t.name) == "head" and getparam(t, "1") == "ru" and getparam(t, "2") == "verb form":
found_head_verb_form = True
if not found_head_verb_form or not found_inflection_of:
# Find definition line
foundrussian = False
sections = re.split("(^==[^=]*==\n)", unicode(page.text), 0, re.M)
for j in xrange(2, len(sections), 2):
if sections[j-1] == "==Russian==\n":
if foundrussian:
pagemsg("WARNING: Found multiple Russian sections, skipping page")
return
foundrussian = True
deflines = r"\n".join(re.findall(r"^(# .*)$", sections[j], re.M))
if not found_head_verb_form:
pagemsg("WARNING: No {{head|ru|verb form}}: %s" % deflines)
if not found_inflection_of:
pagemsg("WARNING: No 'inflection of': %s" % deflines)
def process_page(index, page, save, verbose):
pagetitle = unicode(page.title())
def pagemsg(txt):
msg("Page %s %s: %s" % (index, pagetitle, txt))
pagemsg("Processing")
text = unicode(page.text)
parsed = blib.parse(page)
found_audio = False
for t in parsed.filter_templates():
if unicode(t.name) == "audio" and getparam(t, "lang") == "ru":
found_audio = True
break
if found_audio:
new_text = re.sub(r"\n*\[\[Category:Russian terms with audio links]]\n*", "\n\n", text)
if new_text != text:
comment = "Remove redundant [[:Category:Russian terms with audio links]]"
if save:
pagemsg("Saving with comment = %s" % comment)
page.text = new_text
page.save(comment=comment)
else:
pagemsg("Would save with comment = %s" % comment)
def process_page(index, page, save, verbose):
pagetitle = unicode(page.title())
def pagemsg(txt):
msg("Page %s %s: %s" % (index, pagetitle, txt))
text = unicode(page.text)
parsed = blib.parse(page)
for t in parsed.filter_templates():
if unicode(t.name) == "ru-IPA":
origt = unicode(t)
if getparam(t, "phon"):
pagemsg("phon= already present: %s" % unicode(t))
else:
phon = getparam(t, "1")
pagemsg("Adding phon=: %s" % unicode(t))
rmparam(t, "1")
t.add("phon", phon)
pagemsg("Replaced %s with %s" % (origt, unicode(t)))
newtext = unicode(parsed)
if newtext != text:
if verbose:
pagemsg("Replacing <<%s>> with <<%s>>" % (text, newtext))
comment = "Add phon= to ru-IPA templates"
if save:
pagemsg("Saving with comment = %s" % comment)
page.text = newtext
page.save(comment=comment)
else:
pagemsg("Would save with comment = %s" % comment)
else:
pagemsg("Skipping")
def process_page(index, page, save, verbose):
pagetitle = unicode(page.title())
def pagemsg(txt):
msg("Page %s %s: %s" % (index, pagetitle, txt))
pagemsg("Processing")
parsed = blib.parse(page)
found_page_head = False
for t in parsed.filter_templates():
found_this_head = False
tname = unicode(t.name)
if tname in ru_head_templates:
headname = tname
found_this_head = True
elif tname == "head" and getparam(t, "1") == "ru":
headtype = getparam(t, "2")
headname = "head|ru|%s" % headtype
if headtype in ru_heads_to_warn_about:
pagemsg("WARNING: Found %s" % headname)
found_this_head = True
if found_this_head:
cat_head_count[headname] = cat_head_count.get(headname, 0) + 1
overall_head_count[headname] = overall_head_count.get(headname, 0) + 1
found_page_head = True
if not found_page_head:
pagemsg("WARNING: No head")
if index % 100 == 0:
output_heads_seen()
def process_page(page, index, parsed):
pagetitle = unicode(page.title())
def pagemsg(txt):
msg("Page %s %s: %s" % (index, pagetitle, txt))
pagemsg("Processing")
text = unicode(page.text)
parsed = blib.parse(page)
notes = []
for t in parsed.filter_templates():
origt = unicode(t)
if unicode(t.name) in ["ru-conj", "ru-conj-old"]:
conjtype = getparam(t, "2")
if conjtype.startswith("3a"):
if [x for x in t.params if unicode(x.value) == "or"]:
pagemsg("WARNING: Skipping multi-arg conjugation: %s" %
unicode(t))
continue
t.add("2", conjtype.replace("3a", "3olda"))
notes.append("rename conj type 3a -> 3olda")
newt = unicode(t)
if origt != newt:
pagemsg("Replaced %s with %s" % (origt, newt))
return unicode(parsed), notes
def process_page(page, index):
global args
pagetitle = unicode(page.title())
def pagemsg(txt):
msg("Page %s %s: %s" % (index, pagetitle, txt))
def expand_text(tempcall):
return blib.expand_text(tempcall, pagetitle, pagemsg, args.verbose)
parsed = blib.parse(page)
for t in parsed.filter_templates():
tn = tname(t)
if tn == "fr-IPA":
posval = getparam(t, "pos")
pos_arg = "|pos=%s" % posval if posval else ""
max_arg = 1
for pronarg in xrange(2, 30):
if getparam(t, str(pronarg)):
max_arg = pronarg
for pronarg in xrange(1, max_arg + 1):
pronval = getparam(t, str(pronarg)) or pagetitle
pron = expand_text(
"{{#invoke:fr-pron|show|%s%s|check_new_module=1}}" %
(pronval, pos_arg))
if " || " in pron:
pronold, pronnew = pron.split(" || ")
pagemsg(
"WARNING: {{fr-IPA|%s%s}} == %s in old but %s in new" %
(pronval, pos_arg, pronold, pronnew))
else:
pagemsg("{{fr-IPA|%s%s}} == %s in both old and new" %
(pronval, pos_arg, pron))
def process_page(index, page):
pagetitle = unicode(page.title())
def pagemsg(txt):
msg("Page %s %s: %s" % (index, pagetitle, txt))
pagemsg("Processing")
parsed = blib.parse(page)
found_headword_template = False
headword_templates = []
found_invariant_headword_template = False
found_decl_template = False
for t in parsed.filter_templates():
if unicode(t.name) in ["ru-noun", "ru-proper noun"]:
found_headword_template = True
if getparam(t, "3") == "-":
found_invariant_headword_template = True
else:
headword_templates.append(unicode(t))
if unicode(t.name) in ["ru-noun-table", "ru-decl-noun-see"]:
found_decl_template = True
if found_headword_template and not found_invariant_headword_template:
if found_decl_template:
pagemsg("Found old-style headword template(s) %s with decl" %
", ".join(headword_templates))
else:
pagemsg("Found old-style headword template(s) %s without decl" %
", ".join(headword_templates))
def process_page(index, page, save, verbose):
pagetitle = unicode(page.title())
def pagemsg(txt):
msg("Page %s %s: %s" % (index, pagetitle, txt))
def expand_text(tempcall):
return blib.expand_text(tempcall, pagetitle, pagemsg, verbose)
pagemsg("Processing")
parsed = blib.parse(page)
for t in parsed.filter_templates():
if unicode(t.name) in ["ru-conj", "ru-conj-old"] and getparam(
t, "1").startswith("pf"):
if tname == "ru-conj":
tempcall = re.sub(r"\{\{ru-conj", "{{ru-generate-verb-forms",
unicode(t))
else:
tempcall = re.sub(r"\{\{ru-conj-old",
"{{ru-generate-verb-forms|old=y", unicode(t))
result = expand_text(tempcall)
if not result:
pagemsg("WARNING: Error generating forms, skipping")
continue
args = blib.split_generate_args(result)
for base in ["past_pasv_part", "ppp"]:
for i in ["", "2", "3", "4", "5", "6", "7", "8", "9"]:
val = getparam(t, base + i)
if val and val != "-":
val = re.sub("//.*", "", val)
pagemsg(
"Found perfective past passive participle: %s" %
val)
def process_page(page, index, parsed):
pagetitle = unicode(page.title())
def pagemsg(txt):
msg("Page %s %s: %s" % (index, pagetitle, txt))
pagemsg("Processing")
if not pagetitle.endswith(u"ся"):
return
text = unicode(page.text)
notes = []
parsed = blib.parse(page)
for t in parsed.filter_templates():
origt = unicode(t)
if unicode(t.name) in ["ru-decl-adj", "ru-adj-old"] and getparam(t, "suffix") == u"ся":
lemma = getparam(t, "1")
lemma = re.sub(",", u"ся,", lemma)
lemma = re.sub("$", u"ся", lemma)
t.add("1", lemma)
rmparam(t, "suffix")
notes.append(u"move suffix=ся to lemma")
newt = unicode(t)
if origt != newt:
pagemsg("Replaced %s with %s" % (origt, newt))
return unicode(parsed), notes
def process_page(index, page, save, verbose):
pagetitle = unicode(page.title())
def pagemsg(txt):
msg("Page %s %s: %s" % (index, pagetitle, txt))
def expand_text(tempcall):
return blib.expand_text(tempcall, pagetitle, pagemsg, verbose)
pagemsg("Processing")
parsed = blib.parse(page)
for t in parsed.filter_templates():
if unicode(t.name) in ["ru-conj", "ru-conj-old"] and getparam(t, "1").startswith("pf"):
if tname == "ru-conj":
tempcall = re.sub(r"\{\{ru-conj", "{{ru-generate-verb-forms", unicode(t))
else:
tempcall = re.sub(r"\{\{ru-conj-old", "{{ru-generate-verb-forms|old=y", unicode(t))
result = expand_text(tempcall)
if not result:
pagemsg("WARNING: Error generating forms, skipping")
continue
args = rulib.split_generate_args(result)
for base in ["past_pasv_part", "ppp"]:
for i in ["", "2", "3", "4", "5", "6", "7", "8", "9"]:
val = getparam(t, base + i)
if val and val != "-":
val = re.sub("//.*", "", val)
pagemsg("Found perfective past passive participle: %s" % val)
def process_page(page, index, parsed):
pagetitle = unicode(page.title())
def pagemsg(txt):
msg("Page %s %s: %s" % (index, pagetitle, txt))
pagemsg("Processing")
text = unicode(page.text)
parsed = blib.parse(page)
notes = []
for t in parsed.filter_templates():
if (unicode(t.name) in ["ru-conj", "ru-conj-old"]
and getparam(t, "2") in ["7a", "7b"]):
if [x for x in t.params if unicode(x.value) == "or"]:
pagemsg("WARNING: Skipping multi-arg conjugation: %s" %
unicode(t))
continue
if t.has("past_adv_part_short") and getparam(
t, "past_adv_part_short") == "":
notes.append("set past_adv_part_short=-")
origt = unicode(t)
t.add("past_adv_part_short", "-")
pagemsg("Replacing %s with %s" % (origt, unicode(t)))
if t.has("past_actv_part") and getparam(t, "past_actv_part") == "":
notes.append("set past_actv_part=-")
origt = unicode(t)
t.add("past_actv_part", "-")
pagemsg("Replacing %s with %s" % (origt, unicode(t)))
if new_text != text:
return new_text, notes
if not notes:
pagemsg("WARNING: No changes")
def process_page(page, index, parsed):
pagetitle = unicode(page.title())
def pagemsg(txt):
msg("Page %s %s: %s" % (index, pagetitle, txt))
pagemsg("WARNING: Script no longer applies and would need fixing up")
return
pagemsg("Processing")
text = unicode(page.text)
parsed = blib.parse(page)
notes = []
for t in parsed.filter_templates():
origt = unicode(t)
param1 = getparam(t, "1")
if unicode(t.name) in ["ru-conj"]:
if re.search(r"^6[ac]", param1):
if getparam(t, "no_iotation"):
rmparam(t, "no_iotation")
if param1.startswith("6a"):
notes.append(u"6a + no_iotation -> 6°a")
else:
notes.append(u"6c + no_iotation -> 6°c")
t.add("1", re.sub("^6", u"6°", param1))
elif re.search(r"^6b", param1):
notes.append(u"6b -> 6°b")
t.add("1", re.sub("^6", u"6°", param1))
newt = unicode(t)
if origt != newt:
pagemsg("Replaced %s with %s" % (origt, newt))
return unicode(parsed), notes
def look_up_tonal_form(pagename, pagemsg, verbose):
try:
page = pywikibot.Page(site, pagename)
except Exception as e:
pagemsg("WARNING: Error looking up page %s: %s" %
(pagename, unicode(e)))
return None
try:
if not page.exists():
if verbose:
pagemsg("look_up_tonal_form: Page %s doesn't exist" % pagename)
return None
except Exception as e:
pagemsg("WARNING: Error checking page existence for %s: %s" %
(pagename, unicode(e)))
return None
tonal_forms = []
for t in blib.parse(page).filter_templates():
if unicode(t.name) == "sl-tonal":
if verbose:
pagemsg(
"look_up_tonal_form: For page %s, found tonal template %s"
% (pagename, unicode(t)))
if tonal_forms:
pagemsg(
"WARNING: Found multiple {{sl-tonal}} calls for page %s: new one is %s; can't handle"
% (pagename, unicode(t)))
return None
tonal_forms.append(getparam(t, "1"))
for param in ["2", "3", "4", "5", "6"]:
if getparam(t, param):
tonal_forms.append(getparam(t, param))
return tonal_forms
def process_page(index, page, save, verbose):
pagetitle = unicode(page.title())
def pagemsg(txt):
msg("Page %s %s: %s" % (index, pagetitle, txt))
pagemsg("Processing")
parsed = blib.parse(page)
found_page_head = False
for t in parsed.filter_templates():
found_this_head = False
tname = unicode(t.name)
if tname in ru_head_templates:
headname = tname
found_this_head = True
elif tname == "head" and getparam(t, "1") == "ru":
headtype = getparam(t, "2")
headname = "head|ru|%s" % headtype
if headtype in ru_heads_to_warn_about:
pagemsg("WARNING: Found %s" % headname)
found_this_head = True
if found_this_head:
cat_head_count[headname] = cat_head_count.get(headname, 0) + 1
overall_head_count[headname] = overall_head_count.get(headname, 0) + 1
found_page_head = True
if not found_page_head:
pagemsg("WARNING: No head")
if index % 100 == 0:
output_heads_seen()
def process_page(page, index, parsed):
pagetitle = unicode(page.title())
def pagemsg(txt):
msg("Page %s %s: %s" % (index, pagetitle, txt))
pagemsg("Processing")
text = unicode(page.text)
parsed = blib.parse(page)
notes = []
for t in parsed.filter_templates():
if unicode(t.name) == "ru-phrase":
if t.has("tr"):
pagemsg("WARNING: Has tr=: %s" % unicode(t))
if t.has("head"):
if t.has("1"):
pagemsg("WARNING: Has both head= and 1=: %s" % unicode(t))
else:
notes.append("ru-phrase: convert head= to 1=")
origt = unicode(t)
head = getparam(t, "head")
rmparam(t, "head")
tr = getparam(t, "tr")
rmparam(t, "tr")
t.add("1", head)
if tr:
t.add("tr", tr)
pagemsg("Replacing %s with %s" % (origt, unicode(t)))
return unicode(parsed), notes
def process_page(index, page):
pagetitle = unicode(page.title())
def pagemsg(txt):
msg("Page %s %s: %s" % (index, pagetitle, txt))
pagemsg("Processing")
parsed = blib.parse(page)
found_headword_template = False
for t in parsed.filter_templates():
if unicode(t.name) in ["ru-adj"]:
found_headword_template = True
if not found_headword_template:
notes = []
for t in parsed.filter_templates():
if unicode(t.name) in [
"ru-noun", "ru-noun+", "ru-proper noun", "ru-proper noun+"
]:
notes.append("found noun header (%s)" % unicode(t.name))
if unicode(t.name) == "head":
notes.append("found head header (%s)" % getparam(t, "2"))
pagemsg("Missing adj headword template%s" %
(notes and "; " + ",".join(notes)))
def process_page(page, index):
pagetitle = unicode(page.title())
def pagemsg(txt):
msg("Page %s %s: %s" % (index, pagetitle, txt))
pagemsg("Processing")
parsed = blib.parse(page)
non_wgem = False
wgem = []
for t in parsed.filter_templates():
if tname(t) in ["desc", "desctree"]:
if getparam(t, "bor"):
continue
desc = getparam(t, "1")
if desc in [
"got", "gme-cgo", "non", "non-ogt", "non-own", "non-oen",
"is", "fo", "nrn", "no", "nb", "nn", "sv", "da",
"gmq-osw", "gwq-oda", "gmq-bot", "gmq-jmk", "gmq-scy", "gmq-gut", "ovd"
]:
pagemsg("Saw non-West-Germanic descendant %s" % unicode(t))
non_wgem = True
else:
wgem.append(desc)
if not non_wgem:
pagemsg("Saw no non-West-Germanic descendants but saw West-Germanic or non-Germanic descendants %s" %
",".join(wgem))
def process_page(index, page, save, verbose, direc):
pagetitle = unicode(page.title())
subpagetitle = re.sub(".*:", "", pagetitle)
def pagemsg(txt):
msg("Page %s %s: %s" % (index, pagetitle, txt))
pagemsg("Processing")
notes = []
text = unicode(page.text)
parsed = blib.parse(page)
def frob_gender_param(t, param):
val = getparam(t, param)
if val == "n":
t.add(param, "n-in")
elif val == "n-p":
t.add(param, "n-in-p")
for t in parsed.filter_templates():
if unicode(t.name) in ["ru-noun+", "ru-noun-table"]:
origt = unicode(t)
for param in t.params:
if unicode(param.name) != "1":
pagemsg("WARNING: Found other than a single param in template, skipping: %s" % unicode(t))
return
FIXME
if origt != unicode(t):
param3 = getparam(t, "3")
if param3 != "-":
if fix_indeclinable:
if param3:
pagemsg("WARNING: Can't make indeclinable, has genitive singular given: %s" % origt)
return
else:
t.add("3", "-")
notes.append("make indeclinable")
pagemsg("Making indeclinable: %s" % unicode(t))
else:
pagemsg("WARNING: Would add inanimacy to neuter, but isn't marked as indeclinable: %s" % origt)
return
pagemsg("Replacing %s with %s" % (origt, unicode(t)))
new_text = unicode(parsed)
if new_text != text:
if verbose:
pagemsg("Replacing <%s> with <%s>" % (text, new_text))
if notes:
comment = "Add inanimacy to neuters (%s)" % "; ".join(notes)
else:
comment = "Add inanimacy to neuters"
if save:
pagemsg("Saving with comment = %s" % comment)
page.text = new_text
page.save(comment=comment)
else:
pagemsg("Would save with comment = %s" % comment)
def process_page(index, page, template, new_name, params_to_add,
params_to_remove, params_to_rename, filters, comment):
pagetitle = unicode(page.title())
def pagemsg(txt):
msg("Page %s %s: %s" % (index, pagetitle, txt))
pagemsg("Processing")
notes = []
parsed = blib.parse(page)
for t in parsed.filter_templates():
origt = unicode(t)
tn = tname(t)
if tn == template:
for filt in filters:
m = re.search("^(.*)=(.*)$", filt)
if m:
if getparam(t, m.group(1)) != m.group(2):
pagemsg(
"Skipping %s because filter %s doesn't match" %
origt, filt)
continue
else:
m = re.search("^(.*)~(.*)$", filt)
if m:
if not re.search(m.group(2), getparam(t, m.group(1))):
pagemsg(
"Skipping %s because filter %s doesn't match" %
origt, filt)
continue
else:
raise ValueError("Unrecognized filter %s" % filt)
for old_param, new_param in params_to_rename:
if t.has(old_param):
t.add(new_param,
getparam(t, old_param),
before=old_param,
preserve_spacing=False)
rmparam(t, old_param)
notes.append("rename %s= to %s= in {{%s}}" %
(old_param, new_param, tn))
for param in params_to_remove:
if t.has(param):
rmparam(t, param)
notes.append("remove %s= from {{%s}}" % (param, tn))
for param, value in params_to_add:
if getparam(t, param) != value:
t.add(param, value)
notes.append("add %s=%s to {{%s}}" % (param, value, tn))
if new_name:
blib.set_template_name(t, new_name)
notes.append("rename {{%s}} to {{%s}}" % (template, new_name))
if unicode(t) != origt:
pagemsg("Replaced <%s> with <%s>" % (origt, unicode(t)))
return unicode(parsed), comment or notes
def search_noconj(startFrom, upTo):
for index, page in blib.cat_articles(u"Arabic verbs", startFrom, upTo):
text = unicode(blib.parse(page))
pagetitle = page.title()
if "{{ar-verb" not in text:
msg("* ar-verb not in {{l|ar|%s}}" % pagetitle)
if "{{ar-conj" not in text:
msg("* ar-conj not in {{l|ar|%s}}" % pagetitle)
def process_page(templates, index, page, save=False, verbose=False):
pagetitle = unicode(page.title())
def pagemsg(txt):
msg("Page %s %s: %s" % (index, pagetitle, txt))
if not page.exists():
pagemsg("WARNING: Page doesn't exist")
return
parsed = blib.parse(page)
should_save = False
for t in parsed.filter_templates():
if unicode(t.name) in templates:
origt = unicode(t)
# Punt if multi-arg-set, can't handle yet
should_continue = False
for param in t.params:
if not param.showkey:
val = unicode(param.value)
if val == "or":
pagemsg("WARNING: Can't handle multi-decl templates: %s" % unicode(t))
should_continue = True
break
if val == "-" or val == "_" or val.startswith("join:"):
pagemsg("WARNING: Can't handle multi-word templates: %s" % unicode(t))
should_continue = True
break
if should_continue:
continue
if arg1_is_stress(getparam(t, "1")):
oldplarg = "5"
newplarg = "4"
else:
oldplarg = "4"
newplarg = "3"
plstem = getparam(t, oldplarg)
if plstem:
if getparam(t, newplarg):
pagemsg("WARNING: Something wrong, found args in both positions %s and %s: %s" %
(newplarg, oldplarg, unicode(t)))
continue
rmparam(t, oldplarg)
t.add(newplarg, plstem)
should_save = True
pagemsg("Replacing %s with %s" % (origt, unicode(t)))
if should_save:
comment = "Move plstem from 5th/4th argument to 4th/3rd"
if save:
pagemsg("Saving with comment = %s" % comment)
page.text = unicode(parsed)
page.save(comment=comment)
else:
pagemsg("Would save with comment = %s" % comment)
def process_page(page, index, parsed):
pagetitle = unicode(page.title())
def pagemsg(txt):
msg("Page %s %s: %s" % (index, pagetitle, txt))
pagemsg("Processing")
parsed = blib.parse(page)
notes = []
for t in parsed.filter_templates():
origt = unicode(t)
if unicode(t.name) in ["ru-conj", "ru-conj-old"]:
param1 = getparam(t, "1")
param2 = getparam(t, "2")
if not param2.startswith("7"):
continue
param3 = getparam(t, "3")
param4 = getparam(t, "4")
param5 = getparam(t, "5")
assert not getparam(t, "6")
if param2.startswith("7b"):
if re.search(
u"[еѣ]сти́(сь)?$",
param3) and u"ё" not in param4 and u"ѣ̈" not in param4:
assert not param5
param5 = u"ёе"
param4 = rulib.make_unstressed_ru(param4)
if re.search(u"(л[еѣ]́?зть|с[еѣ]́?сть|обокра́сть)(ся)?$", param3):
param5 = ""
# Fetch non-numbered params.
non_numbered_params = []
for param in t.params:
pname = unicode(param.name)
if not re.search(r"^[0-9]+$", pname) and pname not in [
"lang", "nocat", "tr"
]:
non_numbered_params.append((pname, param.value))
# Erase all params.
del t.params[:]
# Put back numbered params.
t.add("1", param1)
t.add("2", param2)
t.add("3", param3)
t.add("4", param4)
if param5:
t.add("5", param5)
# Put back non-numbered params.
for name, value in non_numbered_params:
t.add(name, value)
newt = unicode(t)
if origt != newt:
pagemsg("Replaced %s with %s" % (origt, newt))
notes.append(
"rewrite class 7 verb to correspond to module changes")
return unicode(parsed), notes
def process_page(index, page, direc):
pagetitle = unicode(page.title())
subpagetitle = re.sub(".*:", "", pagetitle)
def pagemsg(txt):
msg("Page %s %s: %s" % (index, pagetitle, txt))
pagemsg("Processing")
notes = []
text = unicode(page.text)
parsed = blib.parse(page)
def frob_gender_param(t, param):
val = getparam(t, param)
if val == "n":
t.add(param, "n-in")
elif val == "n-p":
t.add(param, "n-in-p")
for t in parsed.filter_templates():
if unicode(t.name) in ["ru-noun+", "ru-noun-table"]:
origt = unicode(t)
for param in t.params:
if unicode(param.name) != "1":
pagemsg(
"WARNING: Found other than a single param in template, skipping: %s"
% unicode(t))
return
FIXME
if origt != unicode(t):
param3 = getparam(t, "3")
if param3 != "-":
if fix_indeclinable:
if param3:
pagemsg(
"WARNING: Can't make indeclinable, has genitive singular given: %s"
% origt)
return
else:
t.add("3", "-")
notes.append("make indeclinable")
pagemsg("Making indeclinable: %s" % unicode(t))
else:
pagemsg(
"WARNING: Would add inanimacy to neuter, but isn't marked as indeclinable: %s"
% origt)
return
pagemsg("Replacing %s with %s" % (origt, unicode(t)))
if notes:
comment = "Add inanimacy to neuters (%s)" % "; ".join(notes)
else:
comment = "Add inanimacy to neuters"
return unicode(parsed), notes
def process_page(index, page, save, verbose):
pagetitle = unicode(page.title())
def pagemsg(txt):
msg("Page %s %s: %s" % (index, pagetitle, txt))
pagemsg("WARNING: Script no longer applies and would need fixing up")
return
pagemsg("Processing")
text = unicode(page.text)
parsed = blib.parse(page)
notes = []
for t in parsed.filter_templates():
origt = unicode(t)
if unicode(t.name) in ["ru-conj"]:
conjtype = getparam(t, "1")
if conjtype.startswith("6a"):
param6 = getparam(t, "6")
if param6:
rmparam(t, "6")
if not getparam(t, "5"):
rmparam(t, "5")
for i in xrange(1, 4):
if not t.has(str(i)):
t.add(str(i), "")
t.add("4", param6)
notes.append("move type 6a arg6 -> arg4")
if conjtype.startswith("7b"):
param7 = getparam(t, "7")
if param7:
rmparam(t, "7")
for i in xrange(1, 6):
if not t.has(str(i)):
t.add(str(i), "")
t.add("6", param7)
notes.append("move type 7b arg7 -> arg6")
newt = unicode(t)
if origt != newt:
pagemsg("Replaced %s with %s" % (origt, newt))
new_text = unicode(parsed)
if new_text != text:
if verbose:
pagemsg("Replacing <%s> with <%s>" % (text, new_text))
assert notes
comment = "; ".join(notes)
if save:
pagemsg("Saving with comment = %s" % comment)
page.text = new_text
page.save(comment=comment)
else:
pagemsg("Would save with comment = %s" % comment)
def process_page(index, page, save, verbose, nouns):
pagetitle = unicode(page.title())
def pagemsg(txt):
msg("Page %s %s: %s" % (index, pagetitle, txt))
def errandpagemsg(txt):
errandmsg("Page %s %s: %s" % (index, pagetitle, txt))
def expand_text(tempcall):
return blib.expand_text(tempcall, pagetitle, pagemsg, verbose)
pagemsg("Processing")
if not re.search(u"[иы]й$", pagetitle):
pagemsg(u"Skipping adjective not in -ый or -ий")
return
noun = re.sub(u"[иы]й$", u"ость", pagetitle)
if noun not in nouns:
return
text = unicode(page.text)
parsed = blib.parse(page)
for t in parsed.filter_templates():
tname = unicode(t.name)
if tname == u"ru-adj-alt-ё":
pagemsg(u"Skipping alt-ё adjective")
return
for t in parsed.filter_templates():
tname = unicode(t.name)
if tname == "ru-adj":
heads = blib.fetch_param_chain(t, "1", "head", pagetitle)
if len(heads) > 1:
pagemsg("Skipping adjective with multiple heads: %s" %
",".join(heads))
return
tr = getparam(t, "tr")
nounsection = blib.find_lang_section(noun, "Russian", pagemsg,
errandpagemsg)
if not nounsection:
pagemsg("Couldn't find Russian section for %s" % noun)
continue
if "==Etymology" in nounsection:
pagemsg("Noun %s already has etymology" % noun)
continue
if tr:
msg(u"%s %s+tr1=%s+-ость no-etym" % (noun, heads[0], tr))
else:
msg(u"%s %s+-ость no-etym" % (noun, heads[0]))
def process_page(page, index, parsed):
pagetitle = unicode(page.title())
def pagemsg(txt):
msg("Page %s %s: %s" % (index, pagetitle, txt))
pagemsg("Processing")
parsed = blib.parse(page)
notes = []
for t in parsed.filter_templates():
origt = unicode(t)
if unicode(t.name) in ["ru-conj", "ru-conj-old"]:
param1 = getparam(t, "1")
param2 = getparam(t, "2")
if not param2.startswith("8b"):
continue
param3 = getparam(t, "3")
param4 = getparam(t, "4")
param5 = getparam(t, "5")
assert not getparam(t, "6")
if getparam(t, "past_m"):
errmsg("WARNING: Has past_m=%s" % getparam(t, "past_m"))
pap = getparam(t, "pap") or getparam(t, "past_adv_part")
if pap:
errmsg("WARNING: Has pap=%s" % pap)
pap2 = getparam(t, "pap2") or getparam(t, "past_adv_part2")
if pap2:
errmsg("WARNING: Has pap2=%s" % pap2)
param4 = rulib.make_unstressed_ru(param4)
# Fetch non-numbered params.
non_numbered_params = []
for param in t.params:
pname = unicode(param.name)
if not re.search(r"^[0-9]+$", pname) and pname not in ["lang", "nocat", "tr"]:
non_numbered_params.append((pname, param.value))
# Erase all params.
del t.params[:]
# Put back numbered params.
t.add("1", param1)
t.add("2", param2)
t.add("3", param3)
t.add("4", param4)
if param5:
t.add("5", param5)
# Put back non-numbered params.
for name, value in non_numbered_params:
t.add(name, value)
newt = unicode(t)
if origt != newt:
pagemsg("Replaced %s with %s" % (origt, newt))
notes.append("rewrite class 8b verb to correspond to module changes")
return unicode(parsed), notes
def process_page(index, page, save, verbose):
pagetitle = unicode(page.title())
def pagemsg(txt):
msg("Page %s %s: %s" % (index, pagetitle, txt))
pagemsg("WARNING: Script no longer applies and would need fixing up")
return
pagemsg("Processing")
text = unicode(page.text)
parsed = blib.parse(page)
notes = []
for t in parsed.filter_templates():
origt = unicode(t)
if unicode(t.name) in ["ru-conj-7a", "ru-conj-7b"]:
past_stem = getparam(t, "4")
vowel_end = re.search(u"[аэыоуяеиёю́]$", past_stem)
past_m = getparam(t, "past_m")
past_f = getparam(t, "past_f")
past_n = getparam(t, "past_n")
past_pl = getparam(t, "past_pl")
if past_m or past_f or past_n or past_pl:
upast_stem = ru.make_unstressed(past_stem)
expected_past_m = past_stem + (u"л" if vowel_end else "")
expected_past_f = upast_stem + u"ла́"
expected_past_n = upast_stem + u"ло́"
expected_past_pl = upast_stem + u"ли́"
if ((not past_m or expected_past_m == past_m) and
expected_past_f == past_f and
expected_past_n == past_n and
expected_past_pl == past_pl):
msg("Would remove past overrides and add arg5=b")
else:
msg("WARNING: Remaining past overrides: past_m=%s, past_f=%s, past_n=%s, past_pl=%s, expected_past_m=%s, expected_past_f=%s, expected_past_n=%s, expected_past_pl=%s" %
(past_m, past_f, past_n, past_pl, expected_past_m, expected_past_f, expected_past_n, expected_past_pl))
newt = unicode(t)
if origt != newt:
pagemsg("Replaced %s with %s" % (origt, newt))
new_text = unicode(parsed)
if new_text != text:
if verbose:
pagemsg("Replacing <%s> with <%s>" % (text, new_text))
assert notes
comment = "; ".join(notes)
if save:
pagemsg("Saving with comment = %s" % comment)
page.text = new_text
page.save(comment=comment)
else:
pagemsg("Would save with comment = %s" % comment)
def process_page(index, page, save, verbose):
pagetitle = unicode(page.title())
def pagemsg(txt):
msg("Page %s %s: %s" % (index, pagetitle, txt))
pagemsg("Processing")
text = unicode(page.text)
parsed = blib.parse(page)
notes = []
for t in parsed.filter_templates():
origt = unicode(t)
param2 = getparam(t, "2")
if unicode(t.name) in ["ru-conj"] and re.search(r"^8[ab]", param2):
if [x for x in t.params if unicode(x.value) == "or"]:
pagemsg("WARNING: Skipping multi-arg conjugation: %s" % unicode(t))
continue
past_m = getparam(t, "past_m")
if past_m:
rmparam(t, "past_m")
stem = getparam(t, "3")
if stem == past_m:
pagemsg("Stem %s and past_m same" % stem)
notes.append("remove redundant past_m %s" % past_m)
elif (param2.startswith("8b") and not param2.startswith("8b/") and
ru.make_unstressed(past_m) == stem):
pagemsg("Class 8b/b and stem %s is unstressed version of past_m %s, replacing stem with past_m" % (
stem, past_m))
t.add("3", past_m)
notes.append("moving past_m %s to arg 3" % past_m)
else:
pagemsg("Stem %s and past_m %s are different, putting past_m in param 5" % (
stem, past_m))
t.add("5", past_m)
notes.append("moving past_m %s to arg 5" % past_m)
newt = unicode(t)
if origt != newt:
pagemsg("Replaced %s with %s" % (origt, newt))
new_text = unicode(parsed)
if new_text != text:
if verbose:
pagemsg("Replacing <%s> with <%s>" % (text, new_text))
assert notes
comment = "; ".join(notes)
if save:
pagemsg("Saving with comment = %s" % comment)
page.text = new_text
page.save(comment=comment)
else:
pagemsg("Would save with comment = %s" % comment)
def process_page(page, index):
pagetitle = unicode(page.title())
def pagemsg(txt):
msg("Page %s %s: %s" % (index, pagetitle, txt))
pagemsg("Processing")
parsed = blib.parse(page)
for t in parsed.filter_templates():
if unicode(t.name) == "R:vep:UVVV":
refpages = blib.fetch_param_chain(t, "1", "")
for refpage in refpages:
if not pywikibot.Page(site, refpage).exists():
pagemsg("Page [[%s]] does not exist" % refpage)
def process_page(index, page, save, verbose):
pagetitle = unicode(page.title())
def pagemsg(txt):
msg("Page %s %s: %s" % (index, pagetitle, txt))
pagemsg("Processing")
parsed = blib.parse(page)
for t in parsed.filter_templates():
if unicode(t.name) == "R:vep:UVVV":
refpages = blib.fetch_param_chain(t, "1", "")
for refpage in refpages:
if not pywikibot.Page(site, refpage).exists():
pagemsg("Page [[%s]] does not exist" % refpage)
def process_lemma(index, pagetitle, slots, program_args):
def pagemsg(txt):
msg("Page %s %s: %s" % (index, pagetitle, txt))
def errandpagemsg(txt):
errandmsg("Page %s %s: %s" % (index, pagetitle, txt))
pagemsg("Processing")
def expand_text(tempcall):
return blib.expand_text(tempcall, pagetitle, pagemsg, program_args.verbose)
page = pywikibot.Page(site, pagetitle)
parsed = blib.parse(page)
for t in parsed.filter_templates():
tn = tname(t)
pos = None
if tn == "la-conj":
pos = "verb"
elif tn == "la-ndecl":
pos = "noun"
elif tn == "la-adecl":
pos = "adj"
if pos:
args = lalib.generate_infl_forms(pos, unicode(t), errandpagemsg, expand_text)
for slot in args:
matches = False
for spec in slots:
if spec == slot:
matches = True
break
if lalib.slot_matches_spec(slot, spec):
matches = True
break
if matches:
for formpagename in re.split(",", args[slot]):
if "[" in formpagename or "|" in formpagename:
pagemsg("WARNING: Skipping page %s with links in it" % formpagename)
else:
formpagename = lalib.remove_macrons(formpagename)
formpage = pywikibot.Page(site, formpagename)
if not formpage.exists():
pagemsg("WARNING: Form page %s doesn't exist, skipping" % formpagename)
elif formpagename == pagetitle:
pagemsg("WARNING: Skipping dictionary form")
else:
def do_process_page(page, index, parsed):
return process_page(index, page, program_args)
blib.do_edit(formpage, index, do_process_page,
save=program_args.save, verbose=program_args.verbose,
diff=program_args.diff)
def process_page(index, page, save, verbose):
pagetitle = unicode(page.title())
def pagemsg(txt):
msg("Page %s %s: %s" % (index, pagetitle, txt))
pagemsg("Processing")
text = unicode(page.text)
parsed = blib.parse(page)
found_inflection_of = False
for t in parsed.filter_templates():
if unicode(t.name) in ["inflection of"]:
found_inflection_of = True
if not found_inflection_of:
pagemsg("WARNING: No 'inflection of'")
def process_page(index, page, save, verbose):
pagetitle = unicode(page.title())
def pagemsg(txt):
msg("Page %s %s: %s" % (index, pagetitle, txt))
pagemsg("Processing")
text = unicode(page.text)
parsed = blib.parse(page)
found_inflection_of = False
for t in parsed.filter_templates():
if unicode(t.name) in ["inflection of"]:
found_inflection_of = True
if not found_inflection_of:
pagemsg("WARNING: No 'inflection of'")
def process_page(page, index, parsed):
pagetitle = unicode(page.title())
def pagemsg(txt):
msg("Page %s %s: %s" % (index, pagetitle, txt))
pagemsg("Processing")
text = unicode(page.text)
newtext = text
parsed = blib.parse(page)
notes = []
for t in parsed.filter_templates():
origt = unicode(t)
tn = tname(t)
# pagemsg("tn=%s" % unicode(tn))
if tn in quote_templates:
text_param = None
if tn in quote_templates_text_param_6:
text_param = "6"
elif tn in quote_templates_text_param_7:
text_param = "7"
elif tn in quote_templates_text_param_8:
text_param = "8"
textval = ""
if text_param:
textval = getparam(t, text_param)
if not textval:
text_param = "text"
textval = getparam(t, text_param)
if not textval:
text_param = "passage"
textval = getparam(t, text_param)
# pagemsg("%s=%s" % (text_param, textval))
textval = textval.strip()
if re.search(r"^\{\{ja-usex\|.*\}\}$", textval, re.S):
rmparam(t, text_param)
newnewtext = re.sub(r"(\n#+\*) *%s" % re.escape(origt),
r"\1 %s\1: %s" % (unicode(t), textval), newtext)
if newtext == newnewtext:
pagemsg("WARNING: Can't find quote template in text: %s" % origt)
else:
newtext = newnewtext
notes.append("move ja-usex call outside of %s call" % tn)
elif "{{ja-usex|" in textval:
pagemsg("WARNING: Found {{ja-usex| embedded in quote text but not whole param: %s" %
origt)
return newtext, notes
def process_page(page, index, do_noun):
pagetitle = unicode(page.title())
def pagemsg(txt):
msg("Page %s %s: %s" % (index, pagetitle, txt))
pagemsg("Processing")
text = unicode(page.text)
parsed = blib.parse(page)
cat = do_noun and "nouns" or "proper nouns"
new_text = re.sub(r"\n\n\n*\[\[Category:Russian %s]]\n\n\n*" % cat, "\n\n",
text)
new_text = re.sub(r"\[\[Category:Russian %s]]\n" % cat, "", new_text)
return new_text, "Remove redundant [[:Category:Russian %s]]"
def search_iyya_noetym(startFrom, upTo):
for page, index in blib.cat_articles(u"Arabic nouns", startFrom, upTo):
text = blib.parse(page)
pagetitle = page.title()
etym = False
suffix = False
if pagetitle.endswith(u"ية"):
for t in text.filter_templates():
if t.name in ["ar-etym-iyya", "ar-etym-nisba-a",
"ar-etym-noun-nisba", "ar-etym-noun-nisba-linking"]:
etym = True
if t.name == "suffix":
suffix = True
if not etym:
msg("Page %s %s: Ends with -iyya, no appropriate etym template%s" % (
index, pagetitle, " (has suffix template)" if suffix else ""))
def snarf_noun_accents_and_forms(noun, orig_pagemsg):
global args
pagetitle = bglib.remove_accents(noun)
if pagetitle in nouns_to_accents_and_forms:
return nouns_to_accents_and_forms[pagetitle]
def pagemsg(txt):
orig_pagemsg("Noun %s: %s" % (noun, txt))
page = pywikibot.Page(site, pagetitle)
parsed = blib.parse(page)
lemma = None
for t in parsed.filter_templates():
if tname(t) in ["bg-noun", "bg-proper noun"]:
if lemma:
pagemsg("WARNING: Saw two {{bg-noun}} invocations without intervening {{bg-ndecl}}: %s" % unicode(t))
lemma = getparam(t, "1")
if not lemma:
pagemsg("WARNING: Missing headword in noun: %s" % unicode(t))
continue
if bglib.needs_accents(lemma):
pagemsg("WARNING: Noun %s missing an accent: %s" % (lemma, unicode(t)))
lemma = False
continue
if tname(t) == "bg-ndecl":
if lemma is False:
pagemsg("WARNING: Skipping %s because noun missing an accent" % unicode(t))
continue
if lemma is None:
pagemsg("WARNING: Skipping %s because no preceding {{bg-noun}}" % unicode(t))
continue
if pagetitle in nouns_to_accents_and_forms:
pagemsg("WARNING: Saw two {{bg-ndecl}} on the same page: %s" % unicode(t))
nouns_to_accents_and_forms[pagetitle] = (None, None)
return (None, None)
generate_template = re.sub(r"^\{\{bg-ndecl\|", "{{bg-generate-noun-forms|", unicode(t))
def expand_text(tempcall):
return blib.expand_text(tempcall, pagetitle, pagemsg, args.verbose)
generate_result = expand_text(generate_template)
if not generate_result:
nouns_to_accents_and_forms[pagetitle] = (None, None)
return (None, None)
nouns_to_accents_and_forms[pagetitle] = (lemma, blib.split_generate_args(generate_result))
if pagetitle in nouns_to_accents_and_forms:
return nouns_to_accents_and_forms[pagetitle]
pagemsg("WARNING: Couldn't find both lemma and declension")
nouns_to_accents_and_forms[pagetitle] = (None, None)
return (None, None)
def process_page(index, page, save, verbose):
pagetitle = unicode(page.title())
def pagemsg(txt):
msg("Page %s %s: %s" % (index, pagetitle, txt))
pagemsg("WARNING: Script no longer applies and would need fixing up")
return
pagemsg("Processing")
text = unicode(page.text)
parsed = blib.parse(page)
notes = []
for t in parsed.filter_templates():
origt = unicode(t)
param1 = getparam(t, "1")
if unicode(t.name) in ["ru-conj"]:
if re.search(r"^6[ac]", param1):
if getparam(t, "no_iotation"):
rmparam(t, "no_iotation")
if param1.startswith("6a"):
notes.append(u"6a + no_iotation -> 6°a")
else:
notes.append(u"6c + no_iotation -> 6°c")
t.add("1", re.sub("^6", u"6°", param1))
elif re.search(r"^6b", param1):
notes.append(u"6b -> 6°b")
t.add("1", re.sub("^6", u"6°", param1))
newt = unicode(t)
if origt != newt:
pagemsg("Replaced %s with %s" % (origt, newt))
new_text = unicode(parsed)
if new_text != text:
if verbose:
pagemsg("Replacing <%s> with <%s>" % (text, new_text))
assert notes
comment = "; ".join(notes)
if save:
pagemsg("Saving with comment = %s" % comment)
page.text = new_text
page.save(comment=comment)
else:
pagemsg("Would save with comment = %s" % comment)
def process_page(index, page, save, verbose):
pagetitle = unicode(page.title())
def pagemsg(txt):
msg("Page %s %s: %s" % (index, pagetitle, txt))
pagemsg("Processing")
text = unicode(page.text)
parsed = blib.parse(page)
notes = []
for t in parsed.filter_templates():
origt = unicode(t)
if unicode(t.name) == "ru-adj":
comps = blib.fetch_param_chain(t, "2", "comp")
newcomps = []
for comp in comps:
if re.search(u"е́?й$", comp):
regcomp = re.sub(u"(е́?)й$", ur"\1е", comp)
if regcomp in newcomps:
pagemsg("Skipping informal form %s" % comp)
notes.append("remove informal comparative %s" % comp)
else:
pagemsg("WARNING: Found informal form %s without corresponding regular form")
newcomps.append(comp)
else:
newcomps.append(comp)
if comps != newcomps:
blib.set_param_chain(t, newcomps, "2", "comp")
newt = unicode(t)
if origt != newt:
pagemsg("Replaced %s with %s" % (origt, newt))
new_text = unicode(parsed)
if new_text != text:
if verbose:
pagemsg("Replacing <%s> with <%s>" % (text, new_text))
assert notes
comment = "; ".join(notes)
if save:
pagemsg("Saving with comment = %s" % comment)
page.text = new_text
page.save(comment=comment)
else:
pagemsg("Would save with comment = %s" % comment)
def process_page(index, page):
pagetitle = unicode(page.title())
def pagemsg(txt):
msg("Page %s %s: %s" % (index, pagetitle, txt))
pagemsg("Processing")
parsed = blib.parse(page)
found_headword_template = False
found_decl_template = False
for t in parsed.filter_templates():
if unicode(t.name) in ["ru-noun", "ru-proper noun"]:
found_headword_template = True
if unicode(t.name) in ["ru-noun-table", "ru-decl-noun-see"]:
found_decl_template = True
if found_headword_template and not found_decl_template:
pagemsg("Found headword template without decl")
def process_page(index, page, save, verbose):
pagetitle = unicode(page.title())
def pagemsg(txt):
msg("Page %s %s: %s" % (index, pagetitle, txt))
pagemsg("Processing")
text = unicode(page.text)
parsed = blib.parse(page)
notes = []
for t in parsed.filter_templates():
if (unicode(t.name) in ["ru-conj", "ru-conj-old"] and
getparam(t, "2") in ["7a", "7b"]):
if [x for x in t.params if unicode(x.value) == "or"]:
pagemsg("WARNING: Skipping multi-arg conjugation: %s" % unicode(t))
continue
if t.has("past_adv_part_short") and getparam(t, "past_adv_part_short") == "":
notes.append("set past_adv_part_short=-")
origt = unicode(t)
t.add("past_adv_part_short", "-")
pagemsg("Replacing %s with %s" % (origt, unicode(t)))
if t.has("past_actv_part") and getparam(t, "past_actv_part") == "":
notes.append("set past_actv_part=-")
origt = unicode(t)
t.add("past_actv_part", "-")
pagemsg("Replacing %s with %s" % (origt, unicode(t)))
new_text = unicode(parsed)
if new_text != text:
if verbose:
pagemsg("Replacing <%s> with <%s>" % (text, new_text))
assert notes
comment = "; ".join(notes)
if save:
pagemsg("Saving with comment = %s" % comment)
page.text = new_text
page.save(comment=comment)
else:
pagemsg("Would save with comment = %s" % comment)
if not notes:
pagemsg("WARNING: No changes")
def process_page(index, page, save, verbose):
pagetitle = unicode(page.title())
def pagemsg(txt):
msg("Page %s %s: %s" % (index, pagetitle, txt))
pagemsg("Processing")
text = unicode(page.text)
parsed = blib.parse(page)
notes = []
for t in parsed.filter_templates():
if unicode(t.name) == "ru-phrase":
if t.has("tr"):
pagemsg("WARNING: Has tr=: %s" % unicode(t))
if t.has("head"):
if t.has("1"):
pagemsg("WARNING: Has both head= and 1=: %s" % unicode(t))
else:
notes.append("ru-phrase: convert head= to 1=")
origt = unicode(t)
head = getparam(t, "head")
rmparam(t, "head")
tr = getparam(t, "tr")
rmparam(t, "tr")
t.add("1", head)
if tr:
t.add("tr", tr)
pagemsg("Replacing %s with %s" % (origt, unicode(t)))
new_text = unicode(parsed)
if new_text != text:
if verbose:
pagemsg("Replacing <%s> with <%s>" % (text, new_text))
assert notes
comment = "; ".join(notes)
if save:
pagemsg("Saving with comment = %s" % comment)
page.text = new_text
page.save(comment=comment)
else:
pagemsg("Would save with comment = %s" % comment)
def process_page(index, page, save, verbose, do_noun):
pagetitle = unicode(page.title())
def pagemsg(txt):
msg("Page %s %s: %s" % (index, pagetitle, txt))
pagemsg("Processing")
text = unicode(page.text)
parsed = blib.parse(page)
cat = do_noun and "nouns" or "proper nouns"
new_text = re.sub(r"\n\n\n*\[\[Category:Russian %s]]\n\n\n*" % cat, "\n\n", text)
new_text = re.sub(r"\[\[Category:Russian %s]]\n" % cat, "", new_text)
if new_text != text:
comment = "Remove redundant [[:Category:Russian %s]]" % cat
if save:
pagemsg("Saving with comment = %s" % comment)
page.text = new_text
page.save(comment=comment)
else:
pagemsg("Would save with comment = %s" % comment)
def process_page(index, page):
pagetitle = unicode(page.title())
def pagemsg(txt):
msg("Page %s %s: %s" % (index, pagetitle, txt))
pagemsg("Processing")
parsed = blib.parse(page)
found_headword_template = False
for t in parsed.filter_templates():
if unicode(t.name) in ["ru-adj"]:
found_headword_template = True
if not found_headword_template:
notes = []
for t in parsed.filter_templates():
if unicode(t.name) in ["ru-noun", "ru-noun+", "ru-proper noun", "ru-proper noun+"]:
notes.append("found noun header (%s)" % unicode(t.name))
if unicode(t.name) == "head":
notes.append("found head header (%s)" % getparam(t, "2"))
pagemsg("Missing adj headword template%s" % (notes and "; " + ",".join(notes)))
def process_page(index, page, save, verbose):
pagetitle = unicode(page.title())
def pagemsg(txt):
msg("Page %s %s: %s" % (index, pagetitle, txt))
pagemsg("WARNING: Script no longer applies and would need fixing up")
return
pagemsg("Processing")
text = unicode(page.text)
parsed = blib.parse(page)
notes = []
for t in parsed.filter_templates():
origt = unicode(t)
if unicode(t.name) in ["ru-conj-4a"]:
shch = getparam(t, "4")
if shch == u"щ":
t.add("3", getparam(t, "3") + shch)
rmparam(t, "4")
notes.append(u"move param 4 (щ) to param 3")
elif shch:
pagemsg("WARNING: Strange value %s for param 4" % shch)
newt = unicode(t)
if origt != newt:
pagemsg("Replaced %s with %s" % (origt, newt))
new_text = unicode(parsed)
if new_text != text:
if verbose:
pagemsg("Replacing <%s> with <%s>" % (text, new_text))
assert notes
comment = "; ".join(notes)
if save:
pagemsg("Saving with comment = %s" % comment)
page.text = new_text
page.save(comment=comment)
else:
pagemsg("Would save with comment = %s" % comment)
def process_page(index, page, save, verbose):
pagetitle = unicode(page.title())
def pagemsg(txt):
msg("Page %s %s: %s" % (index, pagetitle, txt))
pagemsg("Processing")
text = unicode(page.text)
notes = []
parsed = blib.parse(page)
for t in parsed.filter_templates():
origt = unicode(t)
if unicode(t.name) in ["ru-conj", "ru-conj-old"]:
verbtype = getparam(t, "2")
if verbtype in ["pf", "pf-intr", "pf-refl",
"pf-impers", "pf-intr-impers", "pf-refl-impers",
"impf", "impf-intr", "impf-refl",
"impf-impers", "impf-intr-impers", "impf-refl-impers"]:
conjtype = getparam(t, "1")
t.add("2", conjtype)
t.add("1", verbtype)
notes.append("move verb type from arg 2 to arg 1")
newt = unicode(t)
if origt != newt:
pagemsg("Replaced %s with %s" % (origt, newt))
new_text = unicode(parsed)
if new_text != text:
if verbose:
pagemsg("Replacing <%s> with <%s>" % (text, new_text))
assert notes
comment = "; ".join(notes)
if save:
pagemsg("Saving with comment = %s" % comment)
page.text = new_text
page.save(comment=comment)
else:
pagemsg("Would save with comment = %s" % comment)
def process_page(index, page, save, verbose):
pagetitle = unicode(page.title())
def pagemsg(txt):
msg("Page %s %s: %s" % (index, pagetitle, txt))
pagemsg("Processing")
if not pagetitle.endswith(u"ся"):
return
text = unicode(page.text)
notes = []
parsed = blib.parse(page)
for t in parsed.filter_templates():
origt = unicode(t)
if unicode(t.name) in ["ru-decl-adj", "ru-adj-old"] and getparam(t, "suffix") == u"ся":
lemma = getparam(t, "1")
lemma = re.sub(",", u"ся,", lemma)
lemma = re.sub("$", u"ся", lemma)
t.add("1", lemma)
rmparam(t, "suffix")
notes.append(u"move suffix=ся to lemma")
newt = unicode(t)
if origt != newt:
pagemsg("Replaced %s with %s" % (origt, newt))
new_text = unicode(parsed)
if new_text != text:
if verbose:
pagemsg("Replacing <%s> with <%s>" % (text, new_text))
assert notes
comment = "; ".join(notes)
if save:
pagemsg("Saving with comment = %s" % comment)
page.text = new_text
page.save(comment=comment)
else:
pagemsg("Would save with comment = %s" % comment)
def process_page(index, page, save, verbose, genders):
pagetitle = unicode(page.title())
subpagetitle = re.sub(".*:", "", pagetitle)
def pagemsg(txt):
msg("Page %s %s: %s" % (index, pagetitle, txt))
pagemsg("Processing")
parsed = blib.parse(page)
headword_template = None
for t in parsed.filter_templates():
if unicode(t.name) in ["ru-noun+", "ru-proper noun+"]:
if headword_template:
pagemsg("WARNING: Multiple headword templates, skipping")
return
headword_template = t
if not headword_template:
pagemsg("WARNING: No headword templates, skipping")
return
orig_template = unicode(headword_template)
rmparam(headword_template, "g")
rmparam(headword_template, "g2")
rmparam(headword_template, "g3")
rmparam(headword_template, "g4")
rmparam(headword_template, "g5")
for gnum, g in enumerate(genders):
param = "g" if gnum == 0 else "g" + str(gnum+1)
headword_template.add(param, g)
pagemsg("Replacing %s with %s" % (orig_template, unicode(headword_template)))
comment = "Fix headword gender, substituting new value %s" % ",".join(genders)
if save:
pagemsg("Saving with comment = %s" % comment)
page.text = unicode(parsed)
page.save(comment=comment)
else:
pagemsg("Would save with comment = %s" % comment)
def process_page(index, page, save, verbose):
pagetitle = unicode(page.title())
def pagemsg(txt):
msg("Page %s %s: %s" % (index, pagetitle, txt))
pagemsg("WARNING: Script no longer applies and would need fixing up")
return
pagemsg("Processing")
text = unicode(page.text)
parsed = blib.parse(page)
notes = []
for t in parsed.filter_templates():
origt = unicode(t)
if unicode(t.name) in ["ru-conj-5c", "ru-conj-6b"]:
past_f = getparam(t, "4")
if past_f:
t.add("past_f", past_f, before="4")
rmparam(t, "4")
notes.append("Replace 4= with past_f=")
newt = unicode(t)
if origt != newt:
pagemsg("Replaced %s with %s" % (origt, newt))
new_text = unicode(parsed)
if new_text != text:
if verbose:
pagemsg("Replacing <%s> with <%s>" % (text, new_text))
assert notes
comment = "; ".join(notes)
if save:
pagemsg("Saving with comment = %s" % comment)
page.text = new_text
page.save(comment=comment)
else:
pagemsg("Would save with comment = %s" % comment)
def process_page(index, page, save, verbose):
pagetitle = unicode(page.title())
def pagemsg(txt):
msg("Page %s %s: %s" % (index, pagetitle, txt))
pagemsg("Processing")
text = unicode(page.text)
parsed = blib.parse(page)
notes = []
for t in parsed.filter_templates():
if unicode(t.name) == "ru-ux":
origt = unicode(t)
if t.has("adj"):
pagemsg("Removing adj=")
notes.append("remove adj= from ru-ux")
rmparam(t, "adj")
if t.has("shto"):
pagemsg("Removing shto=")
notes.append("remove shto= from ru-ux")
rmparam(t, "shto")
newt = unicode(t)
if origt != newt:
pagemsg("Replaced %s with %s" % (origt, newt))
new_text = unicode(parsed)
if new_text != text:
if verbose:
pagemsg("Replacing <%s> with <%s>" % (text, new_text))
assert notes
comment = "; ".join(notes)
if save:
pagemsg("Saving with comment = %s" % comment)
page.text = new_text
page.save(comment=comment)
else:
pagemsg("Would save with comment = %s" % comment)
def process_page(index, page, save, verbose):
pagetitle = unicode(page.title())
def pagemsg(txt):
msg("Page %s %s: %s" % (index, pagetitle, txt))
pagemsg("Processing")
cons = u"[бцдфгчйклмнпрствшхзжщ]"
if pagetitle.endswith(u"ство") or (
not re.search(cons + u"[кц][оаяеёыи]$", pagetitle)
and not re.search(cons + cons + u"[оаяеёыи]$", pagetitle)
and
# not re.search(u"[оеё]" + cons + "$", pagetitle) and # but too many false positives
not re.search(u"[оеё][кц]$", pagetitle)
):
return
text = unicode(page.text)
parsed = blib.parse(page)
for t in parsed.filter_templates():
tname = unicode(t.name)
if tname == "ru-noun-table" and "*" not in unicode(t):
pagemsg("WARNING: Likely incorrectly-declined reducible: %s" % unicode(t))
def process_page(index, page, save, verbose):
pagetitle = unicode(page.title())
def pagemsg(txt):
msg("Page %s %s: %s" % (index, pagetitle, txt))
pagemsg("Processing")
text = unicode(page.text)
parsed = blib.parse(page)
notes = []
for t in parsed.filter_templates():
origt = unicode(t)
if unicode(t.name) == "wikipedia":
val = getparam(t, "1")
newval = ru.remove_accents(val)
if val != newval:
pagemsg("Removing accents from 1= in {{wikipedia|...}}")
notes.append("remove accents from 1= in {{wikipedia|...}}")
t.add("1", newval)
newt = unicode(t)
if origt != newt:
pagemsg("Replaced %s with %s" % (origt, newt))
new_text = unicode(parsed)
if new_text != text:
if verbose:
pagemsg("Replacing <%s> with <%s>" % (text, new_text))
assert notes
comment = "; ".join(notes)
if save:
pagemsg("Saving with comment = %s" % comment)
page.text = new_text
page.save(comment=comment)
else:
pagemsg("Would save with comment = %s" % comment)
def process_page(index, page, save, verbose):
pagetitle = unicode(page.title())
def pagemsg(txt):
msg("Page %s %s: %s" % (index, pagetitle, txt))
def expand_text(tempcall):
return blib.expand_text(tempcall, pagetitle, pagemsg, verbose)
pagemsg("Processing")
manual_ppp_forms = ["past_pasv_part", "past_pasv_part2", "past_pasv_part3",
"past_pasv_part4", "ppp", "ppp2", "ppp3", "ppp4"]
text = unicode(page.text)
parsed = blib.parse(page)
notes = []
for t in parsed.filter_templates():
origt = unicode(t)
tname = unicode(t.name)
if tname == "ru-conj":
manual_ppps = []
for form in manual_ppp_forms:
ppp = getparam(t, form)
if ppp and ppp != "-":
manual_ppps.append(ppp)
if not manual_ppps:
continue
if [x for x in t.params if unicode(x.value) == "or"]:
pagemsg("WARNING: Skipping multi-arg conjugation: %s" % unicode(t))
continue
curvariant = getparam(t, "2")
if "+p" in curvariant or "(7)" in curvariant or "(8)" in curvariant:
pagemsg("WARNING: Found both manual PPP and PPP variant, something wrong: %s" %
unicode(t))
continue
t2 = blib.parse_text(unicode(t)).filter_templates()[0]
for form in manual_ppp_forms:
rmparam(t2, form)
variants_to_try = ["+p"]
if u"ё" in re.sub(u"ённый$", "", manual_ppps[0]):
variants_to_try.append(u"+pё")
if u"жденный" in manual_ppps[0] or u"ждённый" in manual_ppps[0]:
variants_to_try.append(u"+pжд")
notsamemsgs = []
for variant in variants_to_try:
t2.add("2", curvariant + variant)
tempcall = re.sub(r"\{\{ru-conj", "{{ru-generate-verb-forms", unicode(t2))
result = expand_text(tempcall)
if not result:
pagemsg("WARNING: Error generating forms, skipping")
continue
args = rulib.split_generate_args(result)
if "past_pasv_part" not in args:
pagemsg("WARNING: Something wrong, no past passive participle generated: %s" % unicode(t))
continue
auto_ppps = []
for form in manual_ppp_forms:
if form in args:
for ppp in re.split(",", args[form]):
if ppp and ppp != "-":
auto_ppps.append(ppp)
if manual_ppps == auto_ppps:
pagemsg("Manual PPP's %s same as auto-generated PPP's, switching to auto"
% ",".join(manual_ppps))
for form in manual_ppp_forms:
rmparam(t, form)
t.add("2", curvariant + variant)
notes.append("replaced manual PPP's with variant %s" % variant)
break
else:
notsamemsgs.append("WARNING: Manual PPP's %s not same as auto-generated PPP's %s: %s" %
(",".join(manual_ppps), ",".join(auto_ppps), unicode(t)))
else: # no break in for loop
for m in notsamemsgs:
pagemsg(m)
newt = unicode(t)
if origt != newt:
pagemsg("Replaced %s with %s" % (origt, newt))
new_text = unicode(parsed)
if new_text != text:
if verbose:
pagemsg("Replacing <%s> with <%s>" % (text, new_text))
assert notes
comment = "; ".join(notes)
if save:
pagemsg("Saving with comment = %s" % comment)
page.text = new_text
page.save(comment=comment)
else:
pagemsg("Would save with comment = %s" % comment)