All but backup, yum and bugreport ok now
This commit is contained in:
parent
be348b0b0d
commit
2eb8c32e30
175
lex_scan.py
175
lex_scan.py
@ -5,14 +5,36 @@ import re
|
||||
import sys
|
||||
import json
|
||||
|
||||
# Configure logging
|
||||
logging.basicConfig(level=logging.ERROR, format="%(asctime)s - %(levelname)s - %(message)s")
|
||||
# Configure logger
|
||||
|
||||
#logger.basicConfig(level=logger.WARNING, format="%(asctime)s - %(levelname)s - %(message)s")
|
||||
|
||||
# Create a custom logger
|
||||
logger = logging.getLogger("lex_scan_logger")
|
||||
logger.setLevel(logging.DEBUG) # Set to lowest level needed by any handler
|
||||
|
||||
# Formatter for both handlers
|
||||
formatter = logging.Formatter('%(asctime)s - %(levelname)s - %(message)s')
|
||||
|
||||
# File handler (INFO and above)
|
||||
file_handler = logging.FileHandler('lex_scan.log')
|
||||
file_handler.setLevel(logging.INFO)
|
||||
file_handler.setFormatter(formatter)
|
||||
|
||||
# Console handler (WARNING and above)
|
||||
console_handler = logging.StreamHandler()
|
||||
console_handler.setLevel(logging.WARNING)
|
||||
console_handler.setFormatter(formatter)
|
||||
|
||||
# Add handlers to the logger
|
||||
logger.addHandler(file_handler)
|
||||
logger.addHandler(console_handler)
|
||||
|
||||
missing_files = []
|
||||
|
||||
def validate_panel_name(panel_name):
|
||||
if not panel_name[0].isupper():
|
||||
logging.error(f"Error: Panel name \'{panel_name}\' must start with a capital letter.")
|
||||
logger.error(f"Error: Panel name \'{panel_name}\' must start with a capital letter.")
|
||||
sys.exit(1)
|
||||
|
||||
def get_full_base_path(system):
|
||||
@ -22,7 +44,7 @@ def check_controller_file_exists(system, panel):
|
||||
full_base_path = get_full_base_path(system)
|
||||
controller_path = os.path.join(full_base_path, "lib/SrvMngr/Controller", f"{panel}.pm")
|
||||
if not os.path.exists(controller_path):
|
||||
logging.error(f"Error: Controller file \'{controller_path}\' does not exist.")
|
||||
logger.error(f"Error: Controller file \'{controller_path}\' does not exist.")
|
||||
sys.exit(1)
|
||||
return controller_path
|
||||
|
||||
@ -38,9 +60,9 @@ def extract_title_prefix(controller_path):
|
||||
)
|
||||
if match:
|
||||
prefix = match.group(1)
|
||||
logging.info(f"Extracted prefix: {prefix}")
|
||||
logger.info(f"Extracted prefix: {prefix}")
|
||||
else:
|
||||
logging.error(
|
||||
logger.error(
|
||||
f"Error: Could not find title prefix in '{controller_path}'.\n"
|
||||
"Expected format: my $title = $c->l('<prefix>_something')"
|
||||
)
|
||||
@ -54,15 +76,21 @@ def scan_application_files(system, panel, prefix, scan_general=False):
|
||||
|
||||
# Controller file
|
||||
controller_path = os.path.join(full_base_path, "lib/SrvMngr/Controller", f"{panel}.pm")
|
||||
logging.info(f"Scanning controller file: {controller_path}")
|
||||
logger.info(f"Scanning controller file: {controller_path}")
|
||||
scan_file_for_lexical_strings(controller_path, prefix, extracted_strings, scan_general)
|
||||
|
||||
#Controller file custom code
|
||||
controller_custom_path = os.path.join(full_base_path, "lib/SrvMngr/Controller", f"{panel}-Custom.pm")
|
||||
logger.info(f"Scanning Custom controller file: {controller_custom_path}")
|
||||
scan_file_for_lexical_strings(controller_custom_path, prefix, extracted_strings, scan_general)
|
||||
|
||||
|
||||
# Template files
|
||||
themes = ["default", "AdminLTE"]
|
||||
for theme in themes:
|
||||
template_base_path = os.path.join(full_base_path, "themes", theme, "templates")
|
||||
panel_template_path = os.path.join(template_base_path, f"{panel.lower()}.html.ep")
|
||||
logging.info(f"Scanning panel template file: {panel_template_path}")
|
||||
logger.info(f"Scanning panel template file: {panel_template_path}")
|
||||
scan_file_for_lexical_strings(panel_template_path, prefix, extracted_strings, scan_general)
|
||||
|
||||
# Scan partials
|
||||
@ -72,7 +100,7 @@ def scan_application_files(system, panel, prefix, scan_general=False):
|
||||
# Only scan partial files that match the pattern _<prefix>_<anything>.html.ep
|
||||
if filename.startswith(f"_{prefix.lower()}_") and filename.endswith(".html.ep"):
|
||||
partial_path = os.path.join(partials_dir, filename)
|
||||
logging.info(f"Scanning partial template file: {partial_path}")
|
||||
logger.info(f"Scanning partial template file: {partial_path}")
|
||||
scan_file_for_lexical_strings(partial_path, prefix, extracted_strings, scan_general)
|
||||
|
||||
# Deduplicate lists of dicts in extracted_strings
|
||||
@ -108,45 +136,67 @@ def scan_file_for_lexical_strings(filepath, prefix, extracted_strings_dict, scan
|
||||
# extracted_strings_dict[string].append(filepath)
|
||||
|
||||
# Either scan for strings with a prefix or ones without
|
||||
# and check for dis-allowed characters
|
||||
allowed_pattern = r"[A-Za-z0-9_\-/%:,()\. @]+"
|
||||
if scan_general:
|
||||
pattern = re.compile(r"l[\s|(][\"|\"](.*?)[\"|\"]\)")
|
||||
pattern = re.compile(r"l[\s|(][\"|\'](.*?)[\"|\']\)")
|
||||
found_strings1 = pattern.findall(content)
|
||||
pattern_l_call = re.compile(r"\bl\s*(['\"])(.+?)\1")
|
||||
found_l_calls = [match[1] for match in pattern_l_call.findall(content)]
|
||||
found_strings = found_strings1 + found_l_calls
|
||||
for s in found_strings:
|
||||
if not s.startswith(f"{prefix}_"):
|
||||
# Ignore strings that start with the prefix (with underscore)
|
||||
if s.startswith(f"{prefix}_"):
|
||||
continue
|
||||
s = s.replace(" ","_")
|
||||
#print(f"General:{s} ")
|
||||
if re.fullmatch(allowed_pattern, s):
|
||||
if s not in extracted_strings_dict:
|
||||
extracted_strings_dict[s] = []
|
||||
if filepath not in extracted_strings_dict[s]:
|
||||
extracted_strings_dict[s].append(filepath)
|
||||
else:
|
||||
pattern = re.compile(rf"{prefix}_[a-zA-Z0-9_]+")
|
||||
found_strings = pattern.findall(content)
|
||||
logger.error(f"Unexpected chars ({s}) found in {filepath}")
|
||||
continue
|
||||
else:
|
||||
pattern = re.compile(
|
||||
rf"(['\"])" # opening quote
|
||||
rf"({prefix}_" # prefix and underscore
|
||||
rf"(?:\\.|(?!\1).)*?)" # non-greedy: escaped char or any char not the closing quote
|
||||
rf"\1" # closing quote (same as opening)
|
||||
)
|
||||
|
||||
found_strings = [m.group(2) for m in pattern.finditer(content)]
|
||||
|
||||
for s in found_strings:
|
||||
#print(f"Prefix: {s}")
|
||||
if re.fullmatch(allowed_pattern, s):
|
||||
if s not in extracted_strings_dict:
|
||||
extracted_strings_dict[s] = []
|
||||
if filepath not in extracted_strings_dict[s]:
|
||||
extracted_strings_dict[s].append(filepath)
|
||||
|
||||
else:
|
||||
logger.error(f"Unexpected chars ({s}) found in {filepath}")
|
||||
continue
|
||||
def read_lex_file(filepath):
|
||||
logging.info(f"Reading file: {filepath}")
|
||||
logger.info(f"Reading file: {filepath}")
|
||||
lex_data = {}
|
||||
if not os.path.exists(filepath):
|
||||
logging.warning(f"File not found: {filepath}")
|
||||
missing_files.append(filepath)
|
||||
return lex_data
|
||||
with open(filepath, 'r', encoding='utf-8') as f:
|
||||
content = f.read()
|
||||
# This regex finds all 'key' => 'value' pairs, even if separated by commas or newlines
|
||||
pattern = r"'(.*?)'\s*=>\s*'(.*?)(?<!\\)'"
|
||||
matches = re.findall(pattern, content, re.DOTALL)
|
||||
for key, value in matches:
|
||||
# Unescape single quotes inside values
|
||||
value = value.replace("\\'", "'")
|
||||
# Improved regex: handles single/double quotes and escaped quotes in value
|
||||
pattern = r"""
|
||||
(['"])(.*?)\1 # key in quotes
|
||||
\s*=>\s*
|
||||
(['"])((?:\\.|(?!\3).)*)\3 # value in quotes, allowing escaped chars
|
||||
"""
|
||||
matches = re.findall(pattern, content, re.DOTALL | re.VERBOSE)
|
||||
for _, key, quote, value in matches:
|
||||
# Unescape the quote character and backslashes in value
|
||||
value = value.replace(f"\\{quote}", quote).replace("\\\\", "\\")
|
||||
lex_data[key] = value
|
||||
return lex_data
|
||||
|
||||
|
||||
def write_lex_file(filepath, lex_data):
|
||||
"""
|
||||
Writes a dictionary to a lex file, sorted alphabetically by key (case-insensitive).
|
||||
@ -155,6 +205,7 @@ def write_lex_file(filepath, lex_data):
|
||||
sorted_items = sorted(lex_data.items(), key=lambda item: item[0].lower())
|
||||
with open(filepath, 'w', encoding='utf-8') as f:
|
||||
for key, value in sorted_items:
|
||||
value = value.replace("'",'"')
|
||||
f.write(f"'{key}' => '{value}',{os.linesep}")
|
||||
|
||||
|
||||
@ -173,9 +224,10 @@ def update_file_with_new_lexical_string(filepath, old_string, new_string):
|
||||
new_content = content.replace(old_string, new_string)
|
||||
with open(filepath, 'w') as f:
|
||||
f.write(new_content)
|
||||
logging.info(f"Updated \'{old_string}\' to \'{new_string}\' in file: {filepath}")
|
||||
#map any single quotes to double
|
||||
logger.info(f"Updated \'{old_string}\' to \'{new_string}\' in file: {filepath}")
|
||||
except Exception as e:
|
||||
logging.error(f"Error updating file {filepath}: {e}")
|
||||
logger.error(f"Error updating file {filepath}: {e}")
|
||||
|
||||
|
||||
def export_sorted_missing_lex(input_file1, input_file2, output_file):
|
||||
@ -183,17 +235,6 @@ def export_sorted_missing_lex(input_file1, input_file2, output_file):
|
||||
Reads two lex files, finds all entries in input_file1 missing from input_file2,
|
||||
sorts them alphabetically by key (case-insensitive), and writes them to output_file.
|
||||
"""
|
||||
def read_lex_file(filepath):
|
||||
"""Reads a lex file and returns a dict of key-value pairs."""
|
||||
if not os.path.exists(filepath):
|
||||
print(f"File not found: {filepath}")
|
||||
return {}
|
||||
with open(filepath, 'r', encoding='utf-8') as f:
|
||||
content = f.read()
|
||||
# Regex to find all 'key' => 'value' pairs
|
||||
pattern = r"'([^']+)'\s*=>\s*'(.*?)(?<!\\)'"
|
||||
matches = re.findall(pattern, content, re.DOTALL)
|
||||
return {key: value for key, value in matches}
|
||||
|
||||
dict1 = read_lex_file(input_file1)
|
||||
dict2 = read_lex_file(input_file2)
|
||||
@ -207,7 +248,7 @@ def export_sorted_missing_lex(input_file1, input_file2, output_file):
|
||||
for k in sorted_missing_keys:
|
||||
out.write(f"'{k}' => '{dict1[k]}',\n")
|
||||
|
||||
logging.info(f"Missing lines written to {output_file}:")
|
||||
logger.info(f"Missing lines written to {output_file}:")
|
||||
#for k in sorted_missing_keys:
|
||||
# print(f"'{k}' => '{dict1[k]}',")
|
||||
|
||||
@ -226,17 +267,16 @@ def main():
|
||||
edit_files = args.edit
|
||||
do_lang = args.lang
|
||||
|
||||
logging.info(f"Starting scan for panel: {panel}, system: {system} edit: {edit_files} lang: {do_lang}")
|
||||
#quit(0)
|
||||
logger.warning(f"Lex scan for panel: {panel}, system: {system} edit: {edit_files} lang: {do_lang}\n")
|
||||
|
||||
validate_panel_name(panel)
|
||||
controller_path = check_controller_file_exists(system, panel)
|
||||
prefix = extract_title_prefix(controller_path)
|
||||
|
||||
if prefix:
|
||||
logging.info(f"Scanning application files for strings with prefix \'{prefix}\'...")
|
||||
logger.info(f"Scanning application files for strings with prefix \'{prefix}\'...")
|
||||
extracted_panel_strings = scan_application_files(system, panel, prefix)
|
||||
logging.info(f"Deduplicated extracted panel strings: {len(extracted_panel_strings)} unique strings found.")
|
||||
logger.info(f"Deduplicated extracted panel strings: {len(extracted_panel_strings)} unique strings found.")
|
||||
|
||||
# Process panel-specific English lexical file
|
||||
# Output to current working directory
|
||||
@ -246,11 +286,11 @@ def main():
|
||||
full_base_path = get_full_base_path(system)
|
||||
|
||||
# Corrected capitalization for panel in path
|
||||
en_lex_path = os.path.join(full_base_path, "lib/SrvMngr/I18N/Modules", panel, f"{panel.lower()}_en.lex")
|
||||
en_lex_path = os.path.join(full_base_path, "lib/SrvMngr/I18N/Modules", panel, f"{panel.lower()}_en.lex.bak")
|
||||
en_lex_new_path = os.path.join(panel_lex_output_dir, f"{panel.lower()}_en.lex.new")
|
||||
|
||||
en_lex_data = read_lex_file(en_lex_path)
|
||||
logging.info(f"Original English lex file lines: {len(en_lex_data)}")
|
||||
logger.info(f"Original English lex file lines: {len(en_lex_data)}")
|
||||
new_en_lex_data = {}
|
||||
|
||||
for lex_string in extracted_panel_strings.keys():
|
||||
@ -269,7 +309,7 @@ def main():
|
||||
new_en_lex_data[lex_string] = sometext
|
||||
|
||||
write_lex_file(en_lex_new_path, new_en_lex_data)
|
||||
logging.info(f"Generated {en_lex_new_path}. Lines in new file: {len(new_en_lex_data)}, Lines in original file: {len(en_lex_data)}")
|
||||
logger.info(f"Generated {en_lex_new_path}. Lines in new file: {len(new_en_lex_data)}, Lines in original file: {len(en_lex_data)}")
|
||||
|
||||
#Create file of the ones not in the new lex file
|
||||
output_diff_file = os.path.join(panel_lex_output_dir, f"{panel.lower()}_en.lex.diff")
|
||||
@ -288,7 +328,7 @@ def main():
|
||||
lang_lex_new_path = os.path.join(panel_lex_output_dir, f"{panel.lower()}_{lang_code}.lex.new")
|
||||
|
||||
lang_lex_data = read_lex_file(lang_lex_path)
|
||||
logging.info(f"Original {lang_code} lex file lines: {len(lang_lex_data)}")
|
||||
logger.info(f"Original {lang_code} lex file lines: {len(lang_lex_data)}")
|
||||
new_lang_lex_data = {}
|
||||
|
||||
for lex_string in extracted_panel_strings.keys():
|
||||
@ -300,28 +340,29 @@ def main():
|
||||
new_lang_lex_data[lex_string] = sometext_from_en
|
||||
|
||||
write_lex_file(lang_lex_new_path, new_lang_lex_data)
|
||||
logging.info(f"Generated {lang_lex_new_path}. Lines in new file: {len(new_lang_lex_data)}, Lines in original file: {len(lang_lex_data)}")
|
||||
logger.info(f"Generated {lang_lex_new_path}. Lines in new file: {len(new_lang_lex_data)}, Lines in original file: {len(lang_lex_data)}")
|
||||
|
||||
logging.info("")
|
||||
logging.info("Scanning application files for general lexical strings...")
|
||||
logger.info("")
|
||||
logger.info("Scanning application files for general lexical strings...")
|
||||
extracted_general_strings = scan_application_files(system, panel, prefix, scan_general=True)
|
||||
logging.info(f"Deduplicated extracted general strings: {len(extracted_general_strings)} unique strings found.")
|
||||
logger.info(f"Deduplicated extracted general strings: {len(extracted_general_strings)} unique strings found.")
|
||||
|
||||
general_lex_output_dir = os.path.join(os.getcwd(), "output", "General")
|
||||
os.makedirs(general_lex_output_dir, exist_ok=True)
|
||||
|
||||
general_en_lex_path = os.path.join(full_base_path, "lib/SrvMngr/I18N/Modules", "General", "general_en.lex")
|
||||
general_en_lex_path_orig = os.path.join(full_base_path, "lib/SrvMngr/I18N/Modules", "General", "general_en.lex.bak")
|
||||
general_en_lex_new_path = os.path.join(general_lex_output_dir, "general_en.lex.new")
|
||||
|
||||
general_en_lex_data = read_lex_file(general_en_lex_path)
|
||||
logging.info(f"Original general English lex file lines: {len(general_en_lex_data)}")
|
||||
general_en_lex_data_orig = read_lex_file(general_en_lex_path_orig)
|
||||
logger.info(f"Original general English lex file lines: {len(general_en_lex_data_orig)}")
|
||||
new_general_en_lex_data = read_lex_file(general_en_lex_new_path)
|
||||
|
||||
for lex_string in extracted_general_strings.keys():
|
||||
if lex_string in general_en_lex_data:
|
||||
new_general_en_lex_data[lex_string] = general_en_lex_data[lex_string]
|
||||
if lex_string in general_en_lex_data_orig:
|
||||
new_general_en_lex_data[lex_string] = general_en_lex_data_orig[lex_string]
|
||||
else:
|
||||
sometext = lex_string.replace("_", " ")
|
||||
sometext = sometext.replace("'",'"')
|
||||
# Split into words
|
||||
words = sometext.split()
|
||||
# Lowercase all words, capitalize the first
|
||||
@ -330,9 +371,9 @@ def main():
|
||||
sometext = ' '.join(words)
|
||||
new_general_en_lex_data[lex_string] = sometext
|
||||
write_lex_file(general_en_lex_new_path, new_general_en_lex_data)
|
||||
logging.info(f"Generated {general_en_lex_new_path}. Lines in new file: {len(new_general_en_lex_data)}, Lines in original file: {len(general_en_lex_data)}")
|
||||
logger.info(f"Generated {general_en_lex_new_path}. Lines in new file: {len(new_general_en_lex_data)}, Lines in original file: {len(general_en_lex_data_orig)}")
|
||||
|
||||
logging.info("")
|
||||
logger.info("")
|
||||
if do_lang:
|
||||
for lang_entry in languages:
|
||||
lang_code = lang_entry["code"]
|
||||
@ -343,7 +384,7 @@ def main():
|
||||
general_lang_lex_new_path = os.path.join(general_lex_output_dir, f"general_{lang_code}.lex.new")
|
||||
|
||||
general_lang_lex_data = read_lex_file(general_lang_lex_path)
|
||||
logging.info(f"Original general {lang_code} lex file lines: {len(general_lang_lex_data)}")
|
||||
logger.info(f"Original general {lang_code} lex file lines: {len(general_lang_lex_data)}")
|
||||
new_general_lang_lex_data = {}
|
||||
|
||||
for lex_string in extracted_general_strings.keys():
|
||||
@ -354,11 +395,11 @@ def main():
|
||||
new_general_lang_lex_data[lex_string] = sometext_from_en
|
||||
|
||||
write_lex_file(general_lang_lex_new_path, new_general_lang_lex_data)
|
||||
logging.info(f"Generated {general_lang_lex_new_path}. Lines in new file: {len(new_general_lang_lex_data)}, Lines in original file: {len(general_lang_lex_data)}")
|
||||
logger.info(f"Generated {general_lang_lex_new_path}. Lines in new file: {len(new_general_lang_lex_data)}, Lines in original file: {len(general_lang_lex_data)}")
|
||||
|
||||
logging.info("")
|
||||
logger.info("")
|
||||
if edit_files:
|
||||
logging.info("Handling single-word lexical strings...")
|
||||
logger.info("Handling single-word lexical strings...")
|
||||
for lex_string, filepaths in extracted_panel_strings.items():
|
||||
if lex_string.startswith(f"{prefix}_"):
|
||||
sometext_part = lex_string[len(prefix) + 1:]
|
||||
@ -367,7 +408,7 @@ def main():
|
||||
|
||||
if just_one_word not in new_general_en_lex_data:
|
||||
new_general_en_lex_data[just_one_word] = just_one_word
|
||||
logging.info(f"Added \'{just_one_word}\' to {general_en_lex_new_path}")
|
||||
logger.info(f"Added \'{just_one_word}\' to {general_en_lex_new_path}")
|
||||
write_lex_file(general_en_lex_new_path, new_general_en_lex_data)
|
||||
|
||||
for lang_entry in languages:
|
||||
@ -381,19 +422,19 @@ def main():
|
||||
if just_one_word not in current_general_lang_lex_data:
|
||||
current_general_lang_lex_data[just_one_word] = just_one_word
|
||||
write_lex_file(general_lang_lex_new_path, current_general_lang_lex_data)
|
||||
logging.info(f"Added \'{just_one_word}\' to {general_lang_lex_new_path}")
|
||||
logger.info(f"Added \'{just_one_word}\' to {general_lang_lex_new_path}")
|
||||
|
||||
for filepath in filepaths:
|
||||
update_file_with_new_lexical_string(filepath, lex_string, just_one_word)
|
||||
|
||||
else:
|
||||
logging.error("Could not determine prefix, exiting.")
|
||||
logger.error("Could not determine prefix, exiting.")
|
||||
sys.exit(1)
|
||||
|
||||
if missing_files:
|
||||
logging.warning("The following files were not found:")
|
||||
logger.warning("The following files were not found:")
|
||||
for f in missing_files:
|
||||
logging.warning(f"- {f}")
|
||||
logger.warning(f"- {f}")
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
Loading…
x
Reference in New Issue
Block a user