ocrd 3.0.0a2__tar.gz → 3.0.0b2__tar.gz

{ocrd-3.0.0a2/src/ocrd.egg-info → ocrd-3.0.0b2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ocrd
-Version: 3.0.0a2
+Version: 3.0.0b2
 Summary: OCR-D framework
 Author-email: Konstantin Baierer <unixprog@gmail.com>
 License: Apache License 2.0
@@ -94,17 +94,12 @@ complete stack of OCR-D-related software.
 
 The easiest way to install is via `pip`:
 
-```sh
-pip install ocrd
+    pip install ocrd
 
-# or just the functionality you need, e.g.
-
-pip install ocrd_modelfactory
-```
 
 All Python software released by [OCR-D](https://github.com/OCR-D) requires Python 3.8 or higher.
 
-**NOTE** Some OCR-D-Tools (or even test cases) _might_ reveal an unintended behavior if you have specific environment modifications, like:
+> **NOTE** Some OCR-D tools (or even test cases) _might_ reveal an unintended behavior if you have specific environment modifications, like:
 * using a custom build of [ImageMagick](https://github.com/ImageMagick/ImageMagick), whose format delegates are different from what OCR-D supposes
 * custom Python logging configurations in your personal account
 
@@ -129,7 +124,6 @@ Almost all behaviour of the OCR-D/core software is configured via CLI options an
 
 Some parts of the software are configured via environment variables:
 
-* `OCRD_METS_CACHING`: If set to `true`, access to the METS file is cached, speeding in-memory search and modification.
 * `OCRD_PROFILE`: This variable configures the built-in CPU and memory profiling. If empty, no profiling is done. Otherwise expected to contain any of the following tokens:
   * `CPU`: Enable CPU profiling of processor runs
   * `RSS`: Enable RSS memory profiling
@@ -142,18 +136,46 @@ Some parts of the software are configured via environment variables:
 * `XDG_CONFIG_HOME`: Directory to look for `./ocrd/resources.yml` (i.e. `ocrd resmgr` user database) – defaults to `$HOME/.config`.
 * `XDG_DATA_HOME`: Directory to look for `./ocrd-resources/*` (i.e. `ocrd resmgr` data location) – defaults to `$HOME/.local/share`.
 
-* `OCRD_DOWNLOAD_RETRIES`: Number of times to retry failed attempts for downloads of workspace files.
+* `OCRD_DOWNLOAD_RETRIES`: Number of times to retry failed attempts for downloads of resources or workspace files.
 * `OCRD_DOWNLOAD_TIMEOUT`: Timeout in seconds for connecting or reading (comma-separated) when downloading.
 
+* `OCRD_MISSING_INPUT`: How to deal with missing input files (for some fileGrp/pageId) during processing:
+  * `SKIP`: ignore and proceed with next page's input
+  * `ABORT`: throw `MissingInputFile` exception
+
+* `OCRD_MISSING_OUTPUT`: How to deal with missing output files (for some fileGrp/pageId) during processing:
+  * `SKIP`: ignore and proceed processing next page
+  * `COPY`: fall back to copying input PAGE to output fileGrp for page
+  * `ABORT`: re-throw whatever caused processing to fail
+
+* `OCRD_MAX_MISSING_OUTPUTS`: Maximal rate of skipped/fallback pages among all processed pages before aborting (decimal fraction, ignored if negative).
+
+* `OCRD_EXISTING_OUTPUT`: How to deal with already existing output files (for some fileGrp/pageId) during processing:
+  * `SKIP`: ignore and proceed processing next page
+  * `OVERWRITE`: force writing result to output fileGrp for page
+  * `ABORT`: re-throw `FileExistsError` exception
+
+
 * `OCRD_METS_CACHING`: Whether to enable in-memory storage of OcrdMets data structures for speedup during processing or workspace operations.
 
 * `OCRD_MAX_PROCESSOR_CACHE`: Maximum number of processor instances (for each set of parameters) to be kept in memory (including loaded models) for processing workers or processor servers.
 
+* `OCRD_MAX_PARALLEL_PAGES`: Maximum number of processor threads for page-parallel processing (within each Processor's selected page range, independent of the number of Processing Workers or Processor Servers). If set `>1`, then a METS Server must be used for METS synchronisation.
+
+* `OCRD_PROCESSING_PAGE_TIMEOUT`: Timeout in seconds for processing a single page. If set >0, when exceeded, the same as OCRD_MISSING_OUTPUT applies.
+
 * `OCRD_NETWORK_SERVER_ADDR_PROCESSING`: Default address of Processing Server to connect to (for `ocrd network client processing`).
 * `OCRD_NETWORK_SERVER_ADDR_WORKFLOW`: Default address of Workflow Server to connect to (for `ocrd network client workflow`).
 * `OCRD_NETWORK_SERVER_ADDR_WORKSPACE`: Default address of Workspace Server to connect to (for `ocrd network client workspace`).
 * `OCRD_NETWORK_RABBITMQ_CLIENT_CONNECT_ATTEMPTS`: Number of attempts for a worker to create its queue. Helpful if the rabbitmq-server needs time to be fully started.
 
+* `OCRD_NETWORK_CLIENT_POLLING_SLEEP`: How many seconds to sleep before trying `ocrd network client` again.
+* `OCRD_NETWORK_CLIENT_POLLING_TIMEOUT`: Timeout for a blocking `ocrd network client` (in seconds).
+
+* `OCRD_NETWORK_SOCKETS_ROOT_DIR`: The root directory where all mets server related socket files are created.
+* `OCRD_NETWORK_LOGS_ROOT_DIR`: The root directory where all ocrd_network related file logs are stored.
+
+
 
 ## Packages
 

{ocrd-3.0.0a2 → ocrd-3.0.0b2}/README.md

@@ -47,17 +47,12 @@ complete stack of OCR-D-related software.
 
 The easiest way to install is via `pip`:
 
-```sh
-pip install ocrd
+    pip install ocrd
 
-# or just the functionality you need, e.g.
-
-pip install ocrd_modelfactory
-```
 
 All Python software released by [OCR-D](https://github.com/OCR-D) requires Python 3.8 or higher.
 
-**NOTE** Some OCR-D-Tools (or even test cases) _might_ reveal an unintended behavior if you have specific environment modifications, like:
+> **NOTE** Some OCR-D tools (or even test cases) _might_ reveal an unintended behavior if you have specific environment modifications, like:
 * using a custom build of [ImageMagick](https://github.com/ImageMagick/ImageMagick), whose format delegates are different from what OCR-D supposes
 * custom Python logging configurations in your personal account
 
@@ -82,7 +77,6 @@ Almost all behaviour of the OCR-D/core software is configured via CLI options an
 
 Some parts of the software are configured via environment variables:
 
-* `OCRD_METS_CACHING`: If set to `true`, access to the METS file is cached, speeding in-memory search and modification.
 * `OCRD_PROFILE`: This variable configures the built-in CPU and memory profiling. If empty, no profiling is done. Otherwise expected to contain any of the following tokens:
   * `CPU`: Enable CPU profiling of processor runs
   * `RSS`: Enable RSS memory profiling
@@ -95,18 +89,46 @@ Some parts of the software are configured via environment variables:
 * `XDG_CONFIG_HOME`: Directory to look for `./ocrd/resources.yml` (i.e. `ocrd resmgr` user database) – defaults to `$HOME/.config`.
 * `XDG_DATA_HOME`: Directory to look for `./ocrd-resources/*` (i.e. `ocrd resmgr` data location) – defaults to `$HOME/.local/share`.
 
-* `OCRD_DOWNLOAD_RETRIES`: Number of times to retry failed attempts for downloads of workspace files.
+* `OCRD_DOWNLOAD_RETRIES`: Number of times to retry failed attempts for downloads of resources or workspace files.
 * `OCRD_DOWNLOAD_TIMEOUT`: Timeout in seconds for connecting or reading (comma-separated) when downloading.
 
+* `OCRD_MISSING_INPUT`: How to deal with missing input files (for some fileGrp/pageId) during processing:
+  * `SKIP`: ignore and proceed with next page's input
+  * `ABORT`: throw `MissingInputFile` exception
+
+* `OCRD_MISSING_OUTPUT`: How to deal with missing output files (for some fileGrp/pageId) during processing:
+  * `SKIP`: ignore and proceed processing next page
+  * `COPY`: fall back to copying input PAGE to output fileGrp for page
+  * `ABORT`: re-throw whatever caused processing to fail
+
+* `OCRD_MAX_MISSING_OUTPUTS`: Maximal rate of skipped/fallback pages among all processed pages before aborting (decimal fraction, ignored if negative).
+
+* `OCRD_EXISTING_OUTPUT`: How to deal with already existing output files (for some fileGrp/pageId) during processing:
+  * `SKIP`: ignore and proceed processing next page
+  * `OVERWRITE`: force writing result to output fileGrp for page
+  * `ABORT`: re-throw `FileExistsError` exception
+
+
 * `OCRD_METS_CACHING`: Whether to enable in-memory storage of OcrdMets data structures for speedup during processing or workspace operations.
 
 * `OCRD_MAX_PROCESSOR_CACHE`: Maximum number of processor instances (for each set of parameters) to be kept in memory (including loaded models) for processing workers or processor servers.
 
+* `OCRD_MAX_PARALLEL_PAGES`: Maximum number of processor threads for page-parallel processing (within each Processor's selected page range, independent of the number of Processing Workers or Processor Servers). If set `>1`, then a METS Server must be used for METS synchronisation.
+
+* `OCRD_PROCESSING_PAGE_TIMEOUT`: Timeout in seconds for processing a single page. If set >0, when exceeded, the same as OCRD_MISSING_OUTPUT applies.
+
 * `OCRD_NETWORK_SERVER_ADDR_PROCESSING`: Default address of Processing Server to connect to (for `ocrd network client processing`).
 * `OCRD_NETWORK_SERVER_ADDR_WORKFLOW`: Default address of Workflow Server to connect to (for `ocrd network client workflow`).
 * `OCRD_NETWORK_SERVER_ADDR_WORKSPACE`: Default address of Workspace Server to connect to (for `ocrd network client workspace`).
 * `OCRD_NETWORK_RABBITMQ_CLIENT_CONNECT_ATTEMPTS`: Number of attempts for a worker to create its queue. Helpful if the rabbitmq-server needs time to be fully started.
 
+* `OCRD_NETWORK_CLIENT_POLLING_SLEEP`: How many seconds to sleep before trying `ocrd network client` again.
+* `OCRD_NETWORK_CLIENT_POLLING_TIMEOUT`: Timeout for a blocking `ocrd network client` (in seconds).
+
+* `OCRD_NETWORK_SOCKETS_ROOT_DIR`: The root directory where all mets server related socket files are created.
+* `OCRD_NETWORK_LOGS_ROOT_DIR`: The root directory where all ocrd_network related file logs are stored.
+
+
 
 ## Packages
 

{ocrd-3.0.0a2 → ocrd-3.0.0b2}/README_bashlib.md

@@ -21,6 +21,9 @@ For example:
 * [`ocrd__log`](#ocrd__log)
 * [`ocrd__minversion`](#ocrd__minversion)
 * [`ocrd__dumpjson`](#ocrd__dumpjson)
+* [`ocrd__resolve_resource`](#ocrd__resolve_resource)
+* [`ocrd__show_resource`](#ocrd__show_resource)
+* [`ocrd__list_resources`](#ocrd__list_resources)
 * [`ocrd__usage`](#ocrd__usage)
 * [`ocrd__parse_argv`](#ocrd__parse_argv)
 <!-- END-MARKDOWN-TOC -->
@@ -56,6 +59,10 @@ export OCRD_TOOL_NAME=ocrd-foo-bar
 
 (Which you automatically get from [`ocrd__wrap`](#ocrd__wrap).)
 
+### `ocrd__resolve_resource`
+
+Output given resource file's path.
+
 ### `ocrd__show_resource`
 
 Output given resource file's content.
@@ -88,6 +95,7 @@ This will be filled by the parser along the following keys:
 - `profile`: whether `--profile` is enabled
 - `profile_file`: the argument of `--profile-file`
 - `log_level`: the argument of `--log-level`
+- `mets_server_url`: the argument of `--mets-server-url` argument
 - `mets_file`: absolute path of the `--mets` argument
 - `working_dir`: absolute path of the `--working-dir` argument or the parent of `mets_file`
 - `page_id`: the argument of `--page-id`
@@ -95,7 +103,7 @@ This will be filled by the parser along the following keys:
 - `output_file_grp`: the argument of `--output-file-grp`
 
 Moreover, there will be an associative array **`params`**
-with the fully expanded runtime values of the ocrd-tool.json parameters.
+with the fully validated and default-expanded runtime values of the `ocrd-tool.json` parameters.
 
 ### `ocrd__wrap`
 

ocrd-3.0.0b2/VERSION

@@ -0,0 +1 @@
+3.0.0b2

{ocrd-3.0.0a2 → ocrd-3.0.0b2}/src/ocrd/cli/__init__.py

@@ -10,6 +10,36 @@ import click
 
 from ocrd_utils import config
 
+# pylint: disable=wrong-import-position
+
+def command_with_replaced_help(*replacements):
+
+    class CommandWithReplacedHelp(click.Command):
+        def get_help(self, ctx):
+            newhelp = super().get_help(ctx)
+            for replacement in replacements:
+                newhelp = re.sub(*replacement, newhelp)
+            # print(newhelp)
+            return newhelp
+
+    return CommandWithReplacedHelp
+
+# pylint: enable=wrong-import-position
+
+from ..decorators import ocrd_loglevel
+from .ocrd_tool import ocrd_tool_cli
+from .workspace import workspace_cli
+from .process import process_cli
+from .bashlib import bashlib_cli
+from .validate import validate_cli
+from .resmgr import resmgr_cli
+from .zip import zip_cli
+from .log import log_cli
+from .network import network_cli
+
+
+__all__ = ['cli']
+
 _epilog = f"""
 
 \b
@@ -41,6 +71,10 @@ Variables:
 \b
 {config.describe('OCRD_MAX_PROCESSOR_CACHE')}
 \b
+{config.describe('OCRD_NETWORK_CLIENT_POLLING_SLEEP')}
+\b
+{config.describe('OCRD_NETWORK_CLIENT_POLLING_TIMEOUT')}
+\b
 {config.describe('OCRD_NETWORK_SERVER_ADDR_PROCESSING')}
 \b
 {config.describe('OCRD_NETWORK_SERVER_ADDR_WORKFLOW')}
@@ -60,30 +94,6 @@ Variables:
 {config.describe('OCRD_LOGGING_DEBUG')}
 """
 
-def command_with_replaced_help(*replacements):
-
-    class CommandWithReplacedHelp(click.Command):
-        def get_help(self, ctx):
-            help = super().get_help(ctx)
-            for replacement in replacements:
-                help = re.sub(*replacement, help)
-            # print(help)
-            return help
-
-    return CommandWithReplacedHelp
-
-
-from ..decorators import ocrd_loglevel
-from .ocrd_tool import ocrd_tool_cli
-from .workspace import workspace_cli
-from .process import process_cli
-from .bashlib import bashlib_cli
-from .validate import validate_cli
-from .resmgr import resmgr_cli
-from .zip import zip_cli
-from .log import log_cli
-from .network import network_cli
-
 @click.group(epilog=_epilog)
 @click.version_option(package_name='ocrd')
 @ocrd_loglevel
@@ -101,5 +111,3 @@ cli.add_command(validate_cli)
 cli.add_command(log_cli)
 cli.add_command(resmgr_cli)
 cli.add_command(network_cli)
-
-__all__ = ['cli']

{ocrd-3.0.0a2 → ocrd-3.0.0b2}/src/ocrd/cli/bashlib.py

@@ -8,7 +8,6 @@ OCR-D CLI: bash library
 """
 from __future__ import print_function
 import sys
-from os.path import isfile
 import click
 
 from ocrd.constants import BASHLIB_FILENAME
@@ -23,15 +22,7 @@ from ocrd.decorators import (
     ocrd_loglevel,
     ocrd_cli_wrap_processor
 )
-from ocrd_utils import (
-    is_local_filename,
-    get_local_filename,
-    initLogging,
-    getLogger,
-    make_file_id,
-    config
-)
-from ocrd.resolver import Resolver
+from ocrd_utils import make_file_id
 from ocrd.processor import Processor
 
 # ----------------------------------------------------------------------
@@ -82,6 +73,8 @@ def bashlib_constants(name):
         print(val)
 
 @bashlib_cli.command('input-files')
+@click.option('--ocrd-tool', help="path to ocrd-tool.json of processor to feed", default=None)
+@click.option('--executable', help="name of processor executable in ocrd-tool.json", default=None)
 @click.option('-m', '--mets', help="METS to process", default=DEFAULT_METS_BASENAME)
 @click.option('-w', '--working-dir', help="Working Directory")
 @click.option('-I', '--input-file-grp', help='File group(s) used as input.', default=None)
@@ -96,7 +89,7 @@ def bashlib_constants(name):
 @parameter_option
 @parameter_override_option
 @ocrd_loglevel
-def bashlib_input_files(**kwargs):
+def bashlib_input_files(ocrd_tool, executable, **kwargs):
     """
     List input files for processing
 
@@ -108,12 +101,6 @@ def bashlib_input_files(**kwargs):
     (The printing format is one associative array initializer per line.)
     """
     class BashlibProcessor(Processor):
-        @property
-        def ocrd_tool(self):
-            return {'executable': '', 'steps': ['']}
-        @property
-        def version(self):
-            return '1.0'
         # go half way of the normal run_processor / process_workspace call tree
         # by just delegating to process_workspace, overriding process_page_file
         # to ensure all input files exist locally (without persisting them in the METS)
@@ -129,4 +116,31 @@ def bashlib_input_files(**kwargs):
                 print(f"[{field}]='{value}'", end=' ')
             output_file_id = make_file_id(input_files[0], kwargs['output_file_grp'])
             print(f"[outputFileId]='{output_file_id}'")
-    ocrd_cli_wrap_processor(BashlibProcessor, **kwargs)
+    if ocrd_tool and executable:
+        class FullBashlibProcessor(BashlibProcessor):
+            @property
+            def metadata_location(self):
+                # needed for metadata loading and validation mechanism
+                return ocrd_tool
+            @property
+            def executable(self):
+                # needed for ocrd_tool lookup
+                return executable
+    else:
+        # we have no true metadata file, so fill in just to make it work
+        class FullBashlibProcessor(BashlibProcessor):
+            @property
+            def ocrd_tool(self):
+                # needed to satisfy the validator
+                return {'executable': '',
+                        # required now
+                        'input_file_grp_cardinality': 1,
+                        'output_file_grp_cardinality': 1,
+                        'steps': ['']
+                }
+            @property
+            def version(self):
+                # needed to satisfy the validator and wrapper
+                return '1.0'
+
+    ocrd_cli_wrap_processor(FullBashlibProcessor, **kwargs)

{ocrd-3.0.0a2 → ocrd-3.0.0b2}/src/ocrd/cli/ocrd_tool.py

@@ -17,7 +17,6 @@ from ocrd.decorators import parameter_option, parameter_override_option
 from ocrd.processor import Processor
 from ocrd_utils import (
     set_json_key_value_overrides,
-    VERSION as OCRD_VERSION,
     parse_json_string_or_file,
     parse_json_string_with_comments as loads
 )
@@ -29,23 +28,26 @@ class OcrdToolCtx():
         self.filename = filename
         with codecs.open(filename, encoding='utf-8') as f:
             self.content = f.read()
+            # perhaps the validator should _always_ run (for default expansion)
+            # so validate command only for the report?
             self.json = loads(self.content)
+        self.tool_name = ''
 
         class BashProcessor(Processor):
             @property
-            def metadata(inner_self):
+            def metadata(inner_self): # pylint: disable=no-self-argument,arguments-renamed
                 return self.json
             @property
-            def executable(inner_self):
+            def executable(inner_self): # pylint: disable=no-self-argument,arguments-renamed
                 return self.tool_name
             @property
-            def moduledir(inner_self):
+            def moduledir(inner_self): # pylint: disable=no-self-argument,arguments-renamed
                 return os.path.dirname(self.filename)
             # set docstrings to empty
             __doc__ = None
             # HACK: override the module-level docstring, too
             getmodule(OcrdToolCtx).__doc__ = None
-            def process(inner_self):
+            def process(inner_self): # pylint: disable=no-self-argument,arguments-renamed
                 return super()
 
         self.processor = BashProcessor

{ocrd-3.0.0a2 → ocrd-3.0.0b2}/src/ocrd/cli/workspace.py

@@ -6,7 +6,7 @@ OCR-D CLI: workspace management
     :nested: full
 """
 import os
-from os import getcwd, rmdir, unlink
+from os import rmdir, unlink
 from os.path import dirname, relpath, normpath, exists, join, isabs, isdir
 from pathlib import Path
 from json import loads, dumps
@@ -14,7 +14,6 @@ import sys
 from glob import glob   # XXX pathlib.Path.glob does not support absolute globs
 import re
 import time
-import numpy as np
 
 import click
 
@@ -118,7 +117,7 @@ def workspace_validate(ctx, mets_url, download, skip, page_textequiv_consistency
 @workspace_cli.command('clone', cls=command_with_replaced_help(
     (r' \[WORKSPACE_DIR\]', ''))) # XXX deprecated argument
 @click.option('-f', '--clobber-mets', help="Overwrite existing METS file", default=False, is_flag=True)
-@click.option('-a', '--download', is_flag=True, help="Download all files and change location in METS file after cloning")
+@click.option('-a', '--download', is_flag=True, help="Download all selected files and add local path references in METS file afterwards")
 @click.argument('mets_url')
 @mets_find_options
 # XXX deprecated
@@ -129,8 +128,10 @@ def workspace_clone(ctx, clobber_mets, download, file_grp, file_id, page_id, mim
     Create a workspace from METS_URL and return the directory
 
     METS_URL can be a URL, an absolute path or a path relative to $PWD.
-    If METS_URL is not provided, use --mets accordingly.
     METS_URL can also be an OAI-PMH GetRecord URL wrapping a METS file.
+
+    Additional options pertain to the selection of files / fileGrps / pages
+    to be downloaded, if --download is used.
     """
     LOG = getLogger('ocrd.cli.workspace.clone')
     if workspace_dir:
@@ -143,6 +144,7 @@ def workspace_clone(ctx, clobber_mets, download, file_grp, file_id, page_id, mim
         mets_basename=ctx.mets_basename,
         clobber_mets=clobber_mets,
         download=download,
+        fileGrp=file_grp,
         ID=file_id,
         pageId=page_id,
         mimetype=mimetype,
@@ -408,7 +410,7 @@ def workspace_cli_bulk_add(ctx, regex, mimetype, page_id, file_id, url, local_fi
         if dry_run:
             log.info('workspace.add_file(%s)' % file_dict)
         else:
-            workspace.add_file(fileGrp, ignore=ignore, force=force, **file_dict)
+            workspace.add_file(fileGrp, ignore=ignore, force=force, **file_dict) # pylint: disable=redundant-keyword-arg
 
     # save changes to disk
     workspace.save_mets()
@@ -452,7 +454,7 @@ def workspace_find(ctx, file_grp, mimetype, page_id, file_id, output_field, incl
     snake_to_camel = {"file_id": "ID", "page_id": "pageId", "file_grp": "fileGrp"}
     output_field = [snake_to_camel.get(x, x) for x in output_field]
     modified_mets = False
-    ret = list()
+    ret = []
     workspace = Workspace(
         ctx.resolver,
         directory=ctx.directory,
@@ -748,7 +750,7 @@ def set_id(ctx, id):   # pylint: disable=redefined-builtin
 
 @workspace_cli.command('update-page')
 @click.option('--set', 'attr_value_pairs', help=f"set mets:div ATTR to VALUE. possible keys: {METS_PAGE_DIV_ATTRIBUTE.names()}", metavar="ATTR VALUE", nargs=2, multiple=True)
-@click.option('--order', help="[DEPRECATED - use --set ATTR VALUE", metavar='ORDER')               
+@click.option('--order', help="[DEPRECATED - use --set ATTR VALUE", metavar='ORDER')
 @click.option('--orderlabel', help="DEPRECATED - use --set ATTR VALUE", metavar='ORDERLABEL')
 @click.option('--contentids', help="DEPRECATED - use --set ATTR VALUE", metavar='ORDERLABEL')
 @click.argument('PAGE_ID')
@@ -757,7 +759,7 @@ def update_page(ctx, attr_value_pairs, order, orderlabel, contentids, page_id):
     """
     Update the @ID, @ORDER, @ORDERLABEL, @LABEL or @CONTENTIDS attributes of the mets:div with @ID=PAGE_ID
     """
-    update_kwargs = {k: v for k, v in attr_value_pairs}
+    update_kwargs = dict(attr_value_pairs)
     if order:
         update_kwargs['ORDER'] = order
     if orderlabel:

{ocrd-3.0.0a2 → ocrd-3.0.0b2}/src/ocrd/decorators/__init__.py

@@ -1,4 +1,5 @@
 import sys
+from contextlib import nullcontext
 
 from ocrd_utils import (
     config,
@@ -9,6 +10,7 @@ from ocrd_utils import (
     parse_json_string_with_comments,
     set_json_key_value_overrides,
     parse_json_string_or_file,
+    redirect_stderr_and_stdout_to_file,
 )
 from ocrd_validators import WorkspaceValidator
 from ocrd_network import ProcessingWorker, ProcessorServer, AgentType
@@ -104,10 +106,10 @@ def ocrd_cli_wrap_processor(
         kwargs['parameter'] = parse_json_string_or_file(*kwargs['parameter'],
                                                         resolve_preset_file=resolve)
     else:
-        kwargs['parameter'] = dict()
+        kwargs['parameter'] = {}
     # Merge parameter overrides and parameters
     if 'parameter_override' in kwargs:
-        set_json_key_value_overrides(kwargs['parameter'], *kwargs['parameter_override'])
+        set_json_key_value_overrides(kwargs['parameter'], *kwargs.pop('parameter_override'))
     # Assert -I / -O
     if not kwargs['input_file_grp']:
         raise ValueError('-I/--input-file-grp is required')
@@ -140,17 +142,21 @@ def ocrd_cli_wrap_processor(
         print("Profiling...")
         pr = cProfile.Profile()
         pr.enable()
-        def exit():
+        def goexit():
             pr.disable()
             print("Profiling completed")
             if profile_file:
-                with open(profile_file, 'wb') as f:
-                    pr.dump_stats(profile_file)
+                pr.dump_stats(profile_file)
             s = io.StringIO()
             pstats.Stats(pr, stream=s).sort_stats("cumulative").print_stats()
             print(s.getvalue())
-        atexit.register(exit)
-    run_processor(processorClass, mets_url=mets, workspace=workspace, **kwargs)
+        atexit.register(goexit)
+    if log_filename:
+        log_ctx = redirect_stderr_and_stdout_to_file(log_filename)
+    else:
+        log_ctx = nullcontext()
+    with log_ctx:
+        run_processor(processorClass, mets_url=mets, workspace=workspace, **kwargs)
 
 
 def check_and_run_network_agent(ProcessorClass, subcommand: str, address: str, database: str, queue: str):

{ocrd-3.0.0a2 → ocrd-3.0.0b2}/src/ocrd/lib.bash

@@ -156,6 +156,7 @@ ocrd__parse_argv () {
     while [[ "${1:-}" = -* ]];do
         case "$1" in
             -l|--log-level) ocrd__argv[log_level]=$2 ; shift ;;
+            --log-filename) exec 2> "$2" ; shift ;;
             -h|--help|--usage) ocrd__usage; exit ;;
             -J|--dump-json) ocrd__dumpjson; exit ;;
             -D|--dump-module-dir) echo $(dirname "$OCRD_TOOL_JSON"); exit ;;
@@ -299,6 +300,8 @@ ocrd__wrap () {
         eval "ocrd__files[$i]=ocrd__file$i"
         let ++i
     done < <(ocrd bashlib input-files \
+                  --ocrd-tool $OCRD_TOOL_JSON \
+                  --executable $OCRD_TOOL_NAME \
                   -m "${ocrd__argv[mets_file]}" \
                   -I "${ocrd__argv[input_file_grp]}" \
                   -O "${ocrd__argv[output_file_grp]}" \

{ocrd-3.0.0a2 → ocrd-3.0.0b2}/src/ocrd/mets_server.py

@@ -21,7 +21,7 @@ from pydantic import BaseModel, Field, ValidationError
 import uvicorn
 
 from ocrd_models import OcrdFile, ClientSideOcrdFile, OcrdAgent, ClientSideOcrdAgent
-from ocrd_utils import getLogger, deprecated_alias
+from ocrd_utils import getLogger
 
 
 #
@@ -120,7 +120,7 @@ class ClientSideOcrdMets:
 
     def __init__(self, url, workspace_path: Optional[str] = None):
         self.protocol = "tcp" if url.startswith("http://") else "uds"
-        self.log = getLogger(f"ocrd.mets_client[{url}]")
+        self.log = getLogger(f"ocrd.models.ocrd_mets.client.{url}")
         self.url = url if self.protocol == "tcp" else f'http+unix://{url.replace("/", "%2F")}'
         self.ws_dir_path = workspace_path if workspace_path else None
 
@@ -236,7 +236,7 @@ class ClientSideOcrdMets:
             agent_dict["_type"] = agent_dict.pop("type")
         return [ClientSideOcrdAgent(None, **agent_dict) for agent_dict in agent_dicts]
 
-    def add_agent(self, *args, **kwargs):
+    def add_agent(self, **kwargs):
         if not self.multiplexing_mode:
             return self.session.request("POST", f"{self.url}/agent", json=OcrdAgentModel.create(**kwargs).dict())
         else:
@@ -403,7 +403,6 @@ class OcrdMetsServer:
     @staticmethod
     def kill_process(mets_server_pid: int):
         subprocess_run(args=["kill", "-s", "SIGINT", f"{mets_server_pid}"], shell=False, universal_newlines=True)
-        return
 
     def shutdown(self):
         if self.is_uds:

{ocrd-3.0.0a2 → ocrd-3.0.0b2}/src/ocrd/processor/__init__.py

@@ -3,6 +3,7 @@ from .base import (
     ResourceNotFoundError,
     NonUniqueInputFile,
     MissingInputFile,
+    generate_processor_help,
 )
 from .ocrd_page_result import (
     OcrdPageResult,
@@ -11,5 +12,4 @@ from .ocrd_page_result import (
 from .helpers import (
     run_cli,
     run_processor,
-    generate_processor_help
 )