Chore/code cleanup (#43)

* čištění kódu podle flake8

* Update .gitignore

* Update .gitignore (#41)

* oprava komentářů a překlad do angličtiny

* oprava přihlašování
This commit is contained in:
2026-06-04 17:32:32 +02:00
committed by GitHub
parent b313fc6db0
commit 493696c67b
4 changed files with 732 additions and 360 deletions
+93 -60
View File
@@ -13,20 +13,20 @@ BASE_URL = "https://api.aiscr.cz/2.2/oai"
OUTPUT_FILE = os.path.join(CODELISTS_DIR, 'heslar.csv')
slovnicek = {
'obdobi' : 'heslo:obdobi',
'typ_akce' : 'heslo:akce_typ',
'areal' : 'heslo:areal',
'kraj' : 'ruian_kraj',
'organizace' : 'organizace',
'okres' : 'ruian_okres',
'katastr' : 'ruian_katastr',
'vedouci' : 'osoba',
'pian_presnost' : 'heslo:pian_presnost',
'typ_lokality' : 'heslo:lokalita_typ',
'druh_lokality' : 'heslo:lokalita_druh',
'jistota' : 'heslo:jistota_urceni',
'lokalita_zachovalost' : 'heslo:stav_dochovani',
'pristupnost' : 'heslo:pristupnost'
'obdobi': 'heslo:obdobi',
'typ_akce': 'heslo:akce_typ',
'areal': 'heslo:areal',
'kraj': 'ruian_kraj',
'organizace': 'organizace',
'okres': 'ruian_okres',
'katastr': 'ruian_katastr',
'vedouci': 'osoba',
'pian_presnost': 'heslo:pian_presnost',
'typ_lokality': 'heslo:lokalita_typ',
'druh_lokality': 'heslo:lokalita_druh',
'jistota': 'heslo:jistota_urceni',
'lokalita_zachovalost': 'heslo:stav_dochovani',
'pristupnost': 'heslo:pristupnost'
}
NS = {
@@ -35,30 +35,35 @@ NS = {
'oai_dc': 'http://www.openarchives.org/OAI/2.0/oai_dc/'
}
def ensure_codelists_dir():
"""Creates the codelists directory if it does not exist."""
if not os.path.exists(CODELISTS_DIR):
os.makedirs(CODELISTS_DIR)
def parse_codelist_file(filename, target_dict=None):
"""Reads a CSV codelist file and populates the target dictionary grouped by categories."""
"""
Reads a CSV codelist file and populates
the target dictionary grouped by categories.
"""
if target_dict is None:
target_dict = {}
path = os.path.join(CODELISTS_DIR, filename)
# Return early if the file doesn't exist to avoid missing file errors
if not os.path.exists(path):
if not os.path.exists(path):
return target_dict
try:
# Open the file using standard UTF-8 encoding
with open(path, 'r', encoding='utf-8') as f:
reader = csv.reader(f, delimiter=';')
# Skip the CSV header row
next(reader, None)
next(reader, None)
# Iterate through rows and extract label, code, and category
for row in reader:
if len(row) >= 3:
@@ -66,18 +71,24 @@ def parse_codelist_file(filename, target_dict=None):
code = row[1].strip()
cat = row[2].strip()
clean = code if code else None
# Initialize a new dictionary for a category if encountered for the first time
# Initialize a new dictionary for a category if encountered
# for the first time
if cat not in target_dict:
target_dict[cat] = {}
# Assign the extracted code to the corresponding label within the category
# Assign the extracted code to the corresponding label
# within the category
target_dict[cat][label] = clean
except Exception as e:
QgsMessageLog.logMessage(f"AMČR Codelist Read Error for {filename}: {e}", "AMČR", Qgis.Critical)
QgsMessageLog.logMessage(
f"AMČR Codelist Read Error for {filename}: {e}",
"AMČR", Qgis.Critical)
return target_dict
def load_all_data():
"""Loads the codelist during plugin startup."""
ensure_codelists_dir()
@@ -85,6 +96,7 @@ def load_all_data():
parse_codelist_file('heslar.csv', categorized_data)
return categorized_data
def fetch_set(internal_name, api_set, task=None):
dataset = []
params = {
@@ -92,42 +104,60 @@ def fetch_set(internal_name, api_set, task=None):
"metadataPrefix": "oai_dc",
"set": api_set
}
while True:
# Kontrola zrušení v každém kroku
# Check for cancellation at each iteration
if task and task.isCanceled():
return None
try:
response = requests.get(BASE_URL, params=params, timeout=30)
response.raise_for_status()
root = ET.fromstring(response.content) # nosec
root = ET.fromstring(response.content) # nosec
records = root.findall('.//oai:record', NS)
for rec in records:
metadata = rec.find('.//oai_dc:dc', NS)
if metadata is not None:
# Kód (identifier)
kod = metadata.find('dc:identifier', NS).text if metadata.find('dc:identifier', NS) is not None else ""
# Název (title) - filtrujeme systémové popisky "AMČR - ..."
# Code (identifier)
identifier_el = metadata.find('dc:identifier', NS)
kod = (
identifier_el.text
if identifier_el is not None
else ""
)
# Title filter out system labels "AMČR - ..."
titles = metadata.findall('dc:title', NS)
nazev = ""
for t in titles:
if t.text and not t.text.startswith("AMČR -") and not t.text.startswith(" AMČR -"):
if (
t.text
and not t.text.startswith("AMČR -")
and not t.text.startswith(" AMČR -")
):
nazev = t.text
break
# Pokud by náhodou žádný title neprošel filtrem, vezmeme první dostupný
# If no title passed the filter, fall back
# to the first available one
if not nazev and titles:
nazev = titles[0].text
specialni_pripady = ['okres', 'katastr']
if internal_name in specialni_pripady:
kod = nazev
if internal_name == 'pristupnost':
kod = next((t.text for t in titles if t.text and len(t.text) == 1 and t.text.isalpha()), None)
kod = next(
(
t.text for t in titles
if t.text
and len(t.text) == 1
and t.text.isalpha()
),
None
)
dataset.append({
'Název': nazev,
@@ -135,7 +165,7 @@ def fetch_set(internal_name, api_set, task=None):
'Kategorie': internal_name
})
# Stránkování
# Pagination
token = root.find('.//oai:resumptionToken', NS)
if token is not None and token.text:
params = {
@@ -145,40 +175,45 @@ def fetch_set(internal_name, api_set, task=None):
time.sleep(0.5)
else:
break
except Exception as e:
QgsMessageLog.logMessage(f"Chyba u setu {api_set}: {e}", "AMČR", Qgis.Warning)
QgsMessageLog.logMessage(
f"Chyba u setu {api_set}: {e}",
"AMČR", Qgis.Warning)
break
return dataset
def download_heslare(task=None):
"""Fetches the codelists from the AMČR API and saves it to a CSV file."""
ensure_codelists_dir()
all_data = []
total_sets = len(slovnicek)
for index, (interni, api_nazev) in enumerate(slovnicek.items()):
# Pokud uživatel task zrušil v liště QGISu
# Check if the user cancelled the task via the QGIS taskbar
if task and task.isCanceled():
return False
QgsMessageLog.logMessage(f"Zpracovávám kategorii: {interni}...", "AMČR", Qgis.Info)
# Nyní předáváme task správně do upravené funkce
QgsMessageLog.logMessage(
f"Zpracovávám kategorii: {interni}...",
"AMČR", Qgis.Info)
# Pass the task correctly to the updated fetch function
data = fetch_set(interni, api_nazev, task=task)
if data is None:
return False # Bylo zrušeno uprostřed stahování
return False # Cancelled mid-download
all_data.extend(data)
# Reportování postupu (0-100)
# Report progress (0-100)
if task:
progress = (index + 1) / total_sets * 100
task.setProgress(progress)
# Uložení do CSV
# Save to CSV
with open(OUTPUT_FILE, 'w', newline='', encoding='utf-8-sig') as f:
fieldnames = ['Název', 'Kód', 'Kategorie']
writer = csv.DictWriter(f, fieldnames=fieldnames, delimiter=';')
@@ -187,13 +222,11 @@ def download_heslare(task=None):
return True
def refresh_globals():
"""Znovu načte data ze souborů do globálních proměnných."""
global OBDOBI, TYP_AKCE, AREAL, KRAJE, ORGANIZACE, OKRESY, KATASTRY
global VEDOUCI, PIAN_PRESNOST, TYP_LOKALITY, DRUH_LOKALITY, JISTOTA, LOKALITA_ZACHOVALOST, PRISTUPNOST
"""Reloads data from files into the global variables."""
data = load_all_data()
OBDOBI.clear()
OBDOBI.update(data.get('obdobi', {}))
TYP_AKCE.clear()
@@ -224,7 +257,7 @@ def refresh_globals():
PRISTUPNOST.update(data.get('pristupnost', {}))
# Inicializace prázdných diktů, které se naplní hned pod tím
# Initialize empty dicts that will be populated immediately below
OBDOBI = {}
TYP_AKCE = {}
AREAL = {}
@@ -240,4 +273,4 @@ JISTOTA = {}
LOKALITA_ZACHOVALOST = {}
PRISTUPNOST = {}
refresh_globals()
refresh_globals()