def discover_task_metadata(
self, initial_results: Sequence[Any], additional_data,
**user_args: Union[str, bool]
) -> List[Dict[str, Union[str, Collection[str]]]]:
"""Create a list of metadata that the jobs will need in order to work.
Args:
initial_results:
additional_data:
**user_args:
Returns:
list of dictionaries of job metadata
"""
server_url = self.global_settings.get("getmarc_server_url")
if server_url is None:
raise MissingConfiguration("getmarc_server_url")
return [{
"directory": {
"value": folder.name,
"type": user_args[IDENTIFIER_TYPE],
},
"enhancements": {
"955": user_args.get(OPTION_955_FIELD, False),
"035": user_args.get(OPTION_035_FIELD, False)
},
"api_server": server_url,
"path": folder.path
} for folder in filter(self.filter_bib_id_folders,
os.scandir(user_args[OPTION_USER_INPUT]))]
def discover_task_metadata(self,
initial_results: List[
speedwagon.tasks.Result],
additional_data: Dict[str, Any],
**user_args: str) -> List[dict]:
if self.tessdata_path is not None and \
not os.path.exists(self.tessdata_path):
raise MissingConfiguration("tessdata_path")
new_tasks = []
for result in initial_results:
for image_file in result.data:
image_path = os.path.dirname(image_file)
base_name = os.path.splitext(os.path.basename(image_file))[0]
ocr_file_name = f"{base_name}.txt"
for key, value in ocr.LANGUAGE_CODES.items():
if value == user_args["Language"]:
language_code = key
break
else:
language = user_args["Language"]
raise ValueError(
f"Unable to look up language code for {language}"
)
new_task = {
"source_file_path": image_file,
"destination_path": image_path,
"output_file_name": ocr_file_name,
"lang_code": language_code
}
new_tasks.append(new_task)
return new_tasks
def discover_task_metadata(self, initial_results: List[Any],
additional_data, **user_args) -> List[dict]:
if not os.path.exists(self.tessdata_path):
raise MissingConfiguration("tessdata_path")
new_tasks = []
for result in initial_results:
for image_file in result.data:
image_path = os.path.dirname(image_file)
base_name = os.path.splitext(os.path.basename(image_file))[0]
ocr_file_name = "{}.txt".format(base_name)
for k, v in ocr.LANGUAGE_CODES.items():
if v == user_args["Language"]:
language_code = k
break
else:
raise ValueError("Unable to look up language code "
"for {}".format(user_args["Language"]))
new_task = {
"source_file_path": image_file,
"destination_path": image_path,
"output_file_name": ocr_file_name,
"lang_code": language_code
}
new_tasks.append(new_task)
return new_tasks
def __init__(self, *args, **kwargs) -> None:
super().__init__(*args, **kwargs)
self.global_settings = kwargs.get('global_settings', {})
self.tessdata_path = self.global_settings.get("tessdata")
if self.tessdata_path is None:
raise MissingConfiguration(
"Required setting not configured: tessdata")
if not os.path.exists(self.tessdata_path):
os.mkdir(self.tessdata_path)
description = \
"Create OCR text files for images. \n" \
"\n" \
"Settings: \n" \
" Path: Path containing tiff or jp2 files. \n" \
" Image File Type: The type of Image file to use.\n" \
"\n" \
"\n" \
"Adding Additional Languages:\n" \
" To modify the available languages, place " \
"Tesseract traineddata files for " \
f"version {ocr.Engine(self.tessdata_path).get_version()} " \
"into the following directory:\n" \
"\n" \
f"{self.tessdata_path}.\n" \
"\n" \
"Note:\n" \
" It's important to use the correct version of the " \
"traineddata files. Using incorrect versions won't crash the " \
"program but they may produce unexpected results.\n" \
"\n" \
"For more information about these files, go to " \
"https://github.com/tesseract-ocr/tesseract/wiki/Data-Files\n"
self.set_description(description)
def discover_task_metadata(self, initial_results: Sequence[Any],
additional_data,
**user_args) -> List[Dict[Any, Any]]:
"""Create a list of metadata that the jobs will need in order to work.
Args:
initial_results:
additional_data:
**user_args:
Returns:
list of dictionaries of job metadata
"""
jobs = []
server_url = self.global_settings.get("getmarc_server_url")
if server_url is None:
raise MissingConfiguration("getmarc_server_url")
for folder in filter(self.filter_bib_id_folders,
os.scandir(user_args["Input"])):
jobs.append({
"identifier": {
"value": folder.name,
"type": user_args['Identifier type'],
},
"api_server": server_url,
"path": folder.path
})
return jobs
def __init__(self,
global_settings: Optional[Dict[str, str]] = None) -> None:
"""Generate Marc XML files.
Args:
global_settings:
Settings that could affect the way the workflow runs.
"""
super().__init__()
if global_settings is not None:
self.global_settings = global_settings
for k in GenerateMarcXMLFilesWorkflow.required_settings_keys:
value = self.global_settings.get(k)
if value is None:
raise MissingConfiguration(f"Missing value for {k}")