def match_start_condition(self, line, line_text, line_index, features,
num_lines, prev_line, combined_texts):
# this function get's hopped and called later
# Attention: This is a special case which get's called like:
# lines, lines, self.index_field, feats, len(lines), file_info,None
file_info = prev_line
dbname = file_info.dbname
current_year = int(dbname)
selected_start_index = None
if current_year >= 1960:
# get the first lines which can resemble the title
for index, value in enumerate(line_index):
if value is not False:
break
selected_line = line_text[index]
selected_text = selected_line['text'].strip(",.; ")
if selected_text != "":
selected_start_index = index
break
else:
# just take last line in early years
selected_start_index = len(line_index) - 1
if selected_start_index is not None:
placeholder_match, errors = regu.fuzzy_search(r"", "")
self.do_match_work(True, placeholder_match,
selected_start_index, 0)
return True
return False
def match_start_condition(self, line, line_text, line_index, features,
num_lines, prev_line, combined_texts):
match_start, errors = regu.fuzzy_search(
r"^Hauptsitz\s?:|^Sitz\s?:", line_text)
if match_start is not None:
self.do_match_work(True, match_start, line_index, errors)
return True
def match_start_condition(self, line, line_text, line_index, features,
num_lines, prev_line, combined_texts):
match_start, errors = regu.fuzzy_search(
r"^(Verwaltung:?|Verw\.\s?):", line_text, err_number=0)
if match_start is not None:
self.do_match_work(True, match_start, line_index, errors)
return True
def match_start_condition(self, line, line_text, line_index, features,
num_lines, prev_line, combined_texts):
match_start, errors = regu.fuzzy_search(
r"^(Aufsichtsrat|Kontrollstelle)\s?:", line_text)
if match_start is not None:
self.do_match_work(True, match_start, line_index, errors)
return True
def match_start_condition(self, line, line_text, line_index, features,
num_lines, prev_line, combined_texts):
match_start, errors = regu.fuzzy_search(
r"^(Vorstand|Verwaltungsrat|Verwaltungsbeirat)\s?:", line_text)
if match_start is not None:
self.do_match_work(True, match_start, line_index, errors)
return True
def match_start_condition(self, line, line_text, line_index, features,
num_lines, prev_line, combined_texts):
match_start, errors = regu.fuzzy_search(
r"^(?:Fernschreiber|Telex)\s?:", line_text)
if match_start is not None:
self.do_match_work(True, match_start, line_index, errors)
return True
def match_start_condition(self, line, line_text, line_index, features,
num_lines, prev_line, combined_texts):
match_start, errors = regu.fuzzy_search(
r"^Geschäfts(inhaber|leitung)\s?:", line_text)
if match_start is not None:
self.do_match_work(True, match_start, line_index, errors)
return True
def match_start_condition(self, line, line_text, line_index, features,
num_lines, prev_line, combined_texts):
match_start, errors = regu.fuzzy_search(
r"^Aus.+konsolidiert.+Bilanzen\s?:", line_text)
if match_start is not None:
self.do_match_work(True, match_start, line_index, errors)
return True
def match_stop_condition(self, line, line_text, line_index, features,
num_lines, prev_line, combined_texts):
match_stop, errors = regu.fuzzy_search(r"^Geschäftsjahr\s?:",
line_text)
if match_stop is not None:
self.do_match_work(False, match_stop, line_index, errors)
return True
def match_start_condition(self, line, line_text, line_index, features,
num_lines, prev_line, combined_texts):
match_start, errors = regu.fuzzy_search(r"(^Niederlassungen\s?:)",
line_text,
err_number=1)
if match_start is not None:
self.do_match_work(True, match_start, line_index, errors)
return True
def match_start_condition(self, line, line_text, line_index, features,
num_lines, prev_line, combined_texts):
match_start, errors = regu.fuzzy_search(
r"^Kommandite.+und.+Bank.+:", combined_texts)
if match_start is not None:
self.do_match_work(True, match_start, line_index, errors)
return True
def match_start_condition(self, line, line_text, line_index, features,
num_lines, prev_line, combined_texts):
# matches ss or ß (group is not capturing)
match_start, errors = regu.fuzzy_search(
r"^Aus (der|den) Gewinn- und Verlust- ", line_text)
if match_start is not None:
self.do_match_work(True, match_start, line_index, errors)
return True
def match_start_condition(self, line, line_text, line_index, features,
num_lines, prev_line, combined_texts):
match_start, errors = regu.fuzzy_search(
r"^(Stimmrecht der Aktien|Stimmrecht d\.[.\s]*Aktien.+)\s?:",
line_text)
if match_start is not None:
self.do_match_work(True, match_start, line_index, errors)
return True
def match_start_condition(self, line, line_text, line_index, features,
num_lines, prev_line, combined_texts):
# matches ss or ß (group is not capturing)
match_start, errors = regu.fuzzy_search(
r"^Dividenden(?:.+)aktien\s?:", line_text)
if match_start is not None:
self.do_match_work(True, match_start, line_index, errors)
return True
def match_start_condition(self, line, line_text, line_index, features,
num_lines, prev_line, combined_texts):
match_start, errors = regu.fuzzy_search(
r"Aus.+konsolidiert.+(?:G|g)ewinn.+(?:V|v)erlustrechnungen",
combined_texts)
if match_start is not None:
self.do_match_work(True, match_start, line_index, errors)
return True
def match_start_condition(self, line, line_text, line_index, features,
num_lines, prev_line, combined_texts):
match_start, errors = regu.fuzzy_search(
r"(^Zahlstellen|^Hinterlegungs\- u(nd|\.)\s?Zahlstellen|^Zahlstellen\sbzw.\sHinterlegungsstellen)\s?:",
line_text)
if match_start is not None:
self.do_match_work(True, match_start, line_index, errors)
return True
def match_start_condition(self, line, line_text, line_index, features,
num_lines, prev_line, combined_texts):
match_start, errors = regu.fuzzy_search(
r"(bung der Tochtergesellschaften|^Tochtergesellschaften\sund\ssonstige\sBeteiligungen|^Hauptlagerplatz)\s?:",
line_text)
if match_start is not None:
self.do_match_work(True, match_start, line_index, errors)
return True
def match_start_condition(self, line, line_text, line_index, features,
num_lines, prev_line, combined_texts):
match_start, errors = regu.fuzzy_search(
r"^(Persönlich\shaftender\s)?(Gesellschafter|schafter)\s?:",
line_text)
if match_start is not None:
self.do_match_work(True, match_start, line_index, errors)
return True
def match_start_condition(self, line, line_text, line_index, features,
num_lines, prev_line, combined_texts):
match_start, errors = regu.fuzzy_search(
r"^(Es werden erzeugt|Erzeugnisse|Gegenstand\sdes\sUnternehmens|Produktionsprogramm)\s?:",
line_text,
err_number=1)
if match_start is not None:
self.do_match_work(True, match_start, line_index, errors)
return True
def match_start_condition(self, line, line_text, line_index, features,
num_lines, prev_line, combined_texts):
# matches ss or ß (group is not capturing)
match_start, errors = regu.fuzzy_search(
r"^((Gro(?:ss|ß)aktionär(?:\s?|e\s?))|Aktionäre?)\s?:",
line_text)
if match_start is not None:
self.do_match_work(True, match_start, line_index, errors)
return True
def match_start_condition(self, line, line_text, line_index, features,
num_lines, prev_line, combined_texts):
match_start, errors = regu.fuzzy_search(
r"^(Betriebsanlagen|Betriebsgesellschaften|Vertriebsgesellschaften|Besitzangaben)\s?:",
line_text,
err_number=1)
if match_start is not None:
self.do_match_work(True, match_start, line_index, errors)
return True
def match_start_condition(self, line, line_text, line_index, features,
num_lines, prev_line, combined_texts):
match_start, errors = regu.fuzzy_search(
r"^(Werke in|Werke\s?:|Betriebsstätten\s?:|Eigenwerke\s?:|Zechen\s?:)",
line_text,
err_number=1)
if match_start is not None:
self.do_match_work(True, match_start, line_index, errors)
return True
def match_start_condition(self, line, line_text, line_index, features,
num_lines, prev_line, combined_texts):
# matches ss or ß (group is not capturing)
#match_start, errors = regu.fuzzy_search(r"Aktienkurse\s?.*:", "Aktienkurse (Düsseldorf):")
match_start, errors = regu.fuzzy_search(r"Aktienkurse\s?.*:",
line_text)
if match_start is not None:
self.do_match_work(True, match_start, line_index, errors)
return True
def match_start_condition(self, line, line_text, line_index, features,
num_lines, prev_line, combined_texts):
# reduced error number to prevent confusion with "Beteiligung:"
match_bet, errors = regu.fuzzy_search(
r"(((?:Namhafte|Wesentliche|Maßgebliche|Wichtigste|Sonstige|Direkte)\s?Beteiligung(en)?)|\s?Beteiligung(en)?)\s?:",
line_text,
err_number=0)
if match_bet is not None:
self.do_match_work(True, match_bet, line_index, errors)
return True
def match_start_condition(self, line, line_text, line_index, features,
num_lines, prev_line, combined_texts):
match_start, errors = regu.fuzzy_search(
r"^(?:Fernruf|Telefon)\s?:", line_text)
# if "Kupferberg" in combined_texts:
# print("asd")
if match_start is not None:
self.do_match_work(True, match_start, line_index, errors)
return True
def match_start_condition(self, line, line_text, line_index, features,
num_lines, prev_line, combined_texts):
match_start, errors = regu.fuzzy_search(
r"(^Zweigniederlassungen und Büros\s?:|"
r"^Zweigniederlassungen in\s?:?|"
r"^Zweigniederlassungen\s?:|"
r"^Vertreten\sin\s:|"
r"^Hauptverwaltung\s?:)", line_text)
if match_start is not None:
self.do_match_work(True, match_start, line_index, errors)
return True
def match_start_condition(self, line, line_text, line_index, features,
num_lines, prev_line, combined_texts):
match_start, errors = regu.fuzzy_search(r"^Grundkapital\s?:",
line_text,
err_number=0)
if match_start is not None:
if "Bezugsrechte:" in combined_texts:
return False # this is a special case
self.do_match_work(True, match_start, line_index, errors)
return True
def match_start_condition(self, line, line_text, line_index, features,
num_lines, prev_line, combined_texts):
#if "Bezugsrechtabschläge insgesamt" in line_text:
# return False # false positive, abort
# nd Berichtigungsaktien
regex_string = r"(^Bezugsrechtabschläge insgesamt\s?:|^Umtauschrechte\s?:|^Berichtigunsaktien\s?:|^Bezugsrechte und Berichtigungsaktien\s?:|^Bezugsrechte\s?:)"
match_start, errors = regu.fuzzy_search(regex_string,
combined_texts)
if match_start is not None:
match_line, errors_2 = regu.fuzzy_search(
regex_string, line_text)
# if the current line contains match index current line
if match_line:
pass_index = line_index
else:
# if combination with previous text contains info match previous index
pass_index = line_index - 1
self.do_match_work(True, match_start, pass_index, errors)
return True
def match_start_condition(self, line, line_text, line_index, features,
num_lines, prev_line, combined_texts):
match_start, errors = regu.fuzzy_search(
r"Rechte.+Vorzugs.*(?:a|A)ktien.*:",
combined_texts,
err_number=1)
# mismatch: 'rechtslose Vorzugsaktien. Aktienkurse:' with e2
# match: 'Besondere Rechte der an der Börse Hamburg gehandelten Vorzugs-Aktien:' with e0
# match: 'Besondere Rechte der Vorzugsaktien:' with e0
if match_start is not None:
self.do_match_work(True, match_start, line_index, errors)
return True
def match_start_condition(self, line, line_text, line_index, features,
num_lines, prev_line, combined_texts):
match_start, errors = regu.fuzzy_search(
r"^(Aktionärvertreter)\s?:", line_text)
# this is a possible false positive for above regex
#match_wrong, errors = regu.fuzzy_search(r"^Aktionären", line_text, err_number=1)
if match_start is not None:
match_text = match_start.group()
if "Aktionären" in match_text:
return
self.do_match_work(True, match_start, line_index, errors)
return True