Remove all trailing whitespace

Signed-off-by: Stefan Weil <[email protected]>

Author: stweil

.circleci/config.yml

@@ -16,7 +16,7 @@ jobs:
     steps:
       - checkout
       - run: HOMEBREW_NO_AUTO_UPDATE=1 brew install imagemagick geos
-      - run: make install 
+      - run: make install
       - run: make deps-test test benchmark
 
   test-python36:

.github/workflows/docker-image.yml

@@ -35,4 +35,4 @@ jobs:
       run: |
         docker push ghcr.io/ocrd/core:latest
         docker push ghcr.io/ocrd/core-cuda:latest
-    
+

CHANGELOG.md

@@ -1053,7 +1053,7 @@ Added:
   * Workspace validation will check cardinality of images per file is 1, #243, OCR-D/spec#132
 
 Changed:
-  
+
   * bashlib will no longer warn about "non-conformant" file group names, #365
   * Invalid `file:/` URL will now raise exceptions, #373
   * image_from_*: increase tolerance for size mismatch after rotation to 2px, #371

Makefile

@@ -7,7 +7,7 @@ LOG_LEVEL = INFO
 PYTHONIOENCODING=utf8
 TESTDIR = tests
 
-SPHINX_APIDOC = 
+SPHINX_APIDOC =
 
 BUILD_ORDER = ocrd_utils ocrd_models ocrd_modelfactory ocrd_validators ocrd
 
@@ -52,7 +52,7 @@ DOCKER_TAG = ocrd/core
 DOCKER_BASE_IMAGE = ubuntu:20.04
 
 # Additional arguments to docker build. Default: '$(DOCKER_ARGS)'
-DOCKER_ARGS = 
+DOCKER_ARGS =
 
 # pip install command. Default: $(PIP_INSTALL)
 PIP_INSTALL = $(PIP) install

ocrd/ocrd/lib.bash

@@ -3,14 +3,14 @@
     exit 1
 
 ## ### `ocrd__raise`
-## 
+##
 ## Raise an error and exit.
 ocrd__raise () {
     echo >&2 "ERROR: $1"; exit 127
 }
 
 ## ### `ocrd__log`
-## 
+##
 ## Delegate logging to `ocrd log`
 ocrd__log () {
     local log_level="${ocrd__argv[log_level]:-}"
@@ -23,7 +23,7 @@ ocrd__log () {
 
 
 ## ### `ocrd__minversion`
-## 
+##
 ## Ensure minimum version
 # ht https://stackoverflow.com/posts/4025065
 ocrd__minversion () {
@@ -53,48 +53,48 @@ ocrd__minversion () {
 }
 
 ## ### `ocrd__dumpjson`
-## 
+##
 ## Output ocrd-tool.json.
-## 
+##
 ## Requires `$OCRD_TOOL_JSON` and `$OCRD_TOOL_NAME` to be set:
-## 
+##
 ## ```sh
 ## export OCRD_TOOL_JSON=/path/to/ocrd-tool.json
 ## export OCRD_TOOL_NAME=ocrd-foo-bar
 ## ```
-## 
+##
 ocrd__dumpjson () {
     ocrd ocrd-tool "$OCRD_TOOL_JSON" tool "$OCRD_TOOL_NAME" dump
 }
 
-## 
+##
 ## Output file resource content.
 ##
 ocrd__show_resource () {
     ocrd ocrd-tool "$OCRD_TOOL_JSON" tool "$OCRD_TOOL_NAME" show-resource "$1"
 }
 
-## 
+##
 ## Output file resources names.
 ##
 ocrd__list_resources () {
     ocrd ocrd-tool "$OCRD_TOOL_JSON" tool "$OCRD_TOOL_NAME" list-resources
 }
 
 ## ### `ocrd__usage`
-## 
+##
 ## Print usage
-## 
+##
 ocrd__usage () {
 
     ocrd ocrd-tool "$OCRD_TOOL_JSON" tool "$OCRD_TOOL_NAME" help
 
 }
 
 ## ### `ocrd__parse_argv`
-## 
+##
 ## Expects an associative array ("hash"/"dict") `ocrd__argv` to be defined:
-## 
+##
 ## ```sh
 ## declare -A ocrd__argv=()
 ## ```

ocrd/ocrd/processor/base.py

@@ -43,7 +43,7 @@ class Processor():
     for run-time data processing. That is, it executes a single workflow step,
     or a combination of workflow steps, on the workspace (represented by local METS).
     It reads input files for all or requested physical pages of the input fileGrp(s),
-    and writes output files for them into the output fileGrp(s). It may take 
+    and writes output files for them into the output fileGrp(s). It may take
     a number of optional or mandatory parameters.
     """
 
@@ -163,12 +163,12 @@ def verify(self):
 
     def process(self):
         """
-        Process the :py:attr:`workspace` 
+        Process the :py:attr:`workspace`
         from the given :py:attr:`input_file_grp`
         to the given :py:attr:`output_file_grp`
         for the given :py:attr:`page_id`
         under the given :py:attr:`parameter`.
-        
+
         (This contains the main functionality and needs to be overridden by subclasses.)
         """
         raise Exception("Must be implemented")
@@ -279,7 +279,7 @@ def input_files(self):
         - Otherwise raise an error (complaining that only PAGE-XML warrants
           having multiple images for a single page)
         Algorithm <https://github.com/cisocrgroup/ocrd_cis/pull/57#issuecomment-656336593>_
-        
+
         Returns:
             A list of :py:class:`ocrd_models.ocrd_file.OcrdFile` objects.
         """

ocrd/ocrd/processor/helpers.py

@@ -107,9 +107,9 @@ def run_processor(
         mem_usage = memory_usage(proc=processor.process,
                                 # only run process once
                                 max_iterations=1,
-                                interval=.1, timeout=None, timestamps=True, 
+                                interval=.1, timeout=None, timestamps=True,
                                 # include sub-processes
-                                multiprocess=True, include_children=True, 
+                                multiprocess=True, include_children=True,
                                 # get proportional set size instead of RSS
                                 backend=backend)
         mem_usage_values = [mem for mem, _ in mem_usage]
@@ -198,7 +198,7 @@ def run_cli(
 
 def generate_processor_help(ocrd_tool, processor_instance=None):
     """Generate a string describing the full CLI of this processor including params.
-    
+
     Args:
          ocrd_tool (dict): this processor's ``tools`` section of the module's ``ocrd-tool.json``
          processor_instance (object, optional): the processor implementation
@@ -281,7 +281,7 @@ def wrap(s):
 
 # Taken from https://github.com/OCR-D/core/pull/884
 @freeze_args
-@lru_cache(maxsize=environ.get('OCRD_MAX_PROCESSOR_CACHE', 128))  
+@lru_cache(maxsize=environ.get('OCRD_MAX_PROCESSOR_CACHE', 128))
 def get_cached_processor(parameter: dict, processor_class):
     """
     Call this function to get back an instance of a processor.

ocrd/ocrd/resolver.py

@@ -123,7 +123,7 @@ def workspace_from_url(self, mets_url, dst_dir=None, clobber_mets=False, mets_ba
             download (boolean, False): Whether to also download all the files referenced by the METS
             src_baseurl (string, None): Base URL for resolving relative file locations
 
-        Download (clone) :py:attr:`mets_url` to ``mets.xml`` in :py:attr:`dst_dir`, unless 
+        Download (clone) :py:attr:`mets_url` to ``mets.xml`` in :py:attr:`dst_dir`, unless
         the former is already local and the latter is ``none`` or already identical to its directory name.
 
         Returns:

ocrd/ocrd/resource_manager.py

@@ -168,9 +168,9 @@ def list_installed(self, executable=None):
                     resdict = resdict_list[0]
                 elif str(res_filename.parent) == moduledir:
                     resdict = {
-                        'name': res_name, 
-                        'url': str(res_filename), 
-                        'description': 'Found at module', 
+                        'name': res_name,
+                        'url': str(res_filename),
+                        'description': 'Found at module',
                         'type': res_type,
                         'size': res_size
                     }

ocrd/ocrd/task_sequence.py

@@ -108,7 +108,7 @@ def validate_tasks(tasks, workspace, page_id=None, overwrite=False):
         # TODO disable output_file_grps checks once CLI parameter 'overwrite' is implemented
         # XXX Thu Jan 16 20:14:17 CET 2020 still not sufficiently clever.
         #  if len(prev_output_file_grps) != len(set(prev_output_file_grps)):
-        #      report.add_error("Output file group specified multiple times: %s" % 
+        #      report.add_error("Output file group specified multiple times: %s" %
         #          [grp for grp, count in Counter(prev_output_file_grps).items() if count >= 2])
         prev_output_file_grps += task.output_file_grps
     if not report.is_valid:

ocrd_models/README.md

@@ -36,7 +36,7 @@ Let's say you want to add a method `get_FirstTextRegion` on the `pc:Page` elemen
 
     Would add the method `exportChildren` from a file `exportChildren_PageType.py`.
 
-    > **Note**: 
+    > **Note**:
     > The method name in the file must match the method name passed to
     > `_add_method`. This is *not* checked automatically, so double-check manually!
 

ocrd_models/ocrd_models/ocrd_mets.py

@@ -143,7 +143,7 @@ def _clear_caches(self):
         self._file_cache = None
         self._page_cache = None
         self._fptr_cache = None
-        
+
     def refresh_caches(self):
         if self._cache_flag:
             # Cache for the files (mets:file) - two nested dictionaries
@@ -164,11 +164,11 @@ def refresh_caches(self):
             # The inner dictionary's Key: 'fptr.FILEID'
             # The inner dictionary's Value: a 'fptr' object at some memory location
             self._fptr_cache = {}
-            
+
             # Note, if the empty_mets() function is used to instantiate OcrdMets
             # Then the cache is empty even after this operation
             self._fill_caches()
-        
+
     @property
     def unique_identifier(self):
         """
@@ -179,7 +179,7 @@ def unique_identifier(self):
             found = self._tree.getroot().find('.//mods:identifier[@type="%s"]' % t, NS)
             if found is not None:
                 return found.text
-        
+
     @unique_identifier.setter
     def unique_identifier(self, purl):
         """
@@ -295,7 +295,7 @@ def find_files(self, ID=None, fileGrp=None, pageId=None, mimetype=None, url=None
             mimetype = re.compile(mimetype[REGEX_PREFIX_LEN:])
         if url and url.startswith(REGEX_PREFIX):
             url = re.compile(url[REGEX_PREFIX_LEN:])
-            
+
         candidates = []
         if self._cache_flag:
             if fileGrp:
@@ -307,7 +307,7 @@ def find_files(self, ID=None, fileGrp=None, pageId=None, mimetype=None, url=None
                 candidates = [el_file for id_to_file in self._file_cache.values() for el_file in id_to_file.values()]
         else:
             candidates = self._tree.getroot().xpath('//mets:file', namespaces=NS)
-            
+
         for cand in candidates:
             if ID:
                 if isinstance(ID, str):
@@ -364,11 +364,11 @@ def add_file_group(self, fileGrp):
         if el_fileGrp is None:
             el_fileGrp = ET.SubElement(el_fileSec, TAG_METS_FILEGRP)
             el_fileGrp.set('USE', fileGrp)
-            
+
             if self._cache_flag:
                 # Assign an empty dictionary that will hold the files of the added fileGrp
                 self._file_cache[fileGrp] = {}
-                
+
         return el_fileGrp
 
     def rename_file_group(self, old, new):
@@ -379,7 +379,7 @@ def rename_file_group(self, old, new):
         if el_fileGrp is None:
             raise FileNotFoundError("No such fileGrp '%s'" % old)
         el_fileGrp.set('USE', new)
-        
+
         if self._cache_flag:
             self._file_cache[new] = self._file_cache.pop(old)
 
@@ -427,7 +427,7 @@ def remove_file_group(self, USE, recursive=False, force=False):
 
         if self._cache_flag:
             # Note: Since the files inside the group are removed
-            # with the 'remove_one_file' method above, 
+            # with the 'remove_one_file' method above,
             # we should not take care of that again.
             # We just remove the fileGrp.
             del self._file_cache[el_fileGrp.get('USE')]
@@ -566,7 +566,7 @@ def physical_pages(self):
         """
         if self._cache_flag:
             return list(self._page_cache.keys())
-            
+
         return self._tree.getroot().xpath(
             'mets:structMap[@TYPE="PHYSICAL"]/mets:div[@TYPE="physSequence"]/mets:div[@TYPE="page"]/@ID',
             namespaces=NS)
@@ -579,7 +579,7 @@ def get_physical_pages(self, for_fileIds=None):
         if for_fileIds is None:
             return self.physical_pages
         ret = [None] * len(for_fileIds)
-        
+
         if self._cache_flag:
             for pageId in self._fptr_cache.keys():
                 for fptr in self._fptr_cache[pageId].keys():
@@ -632,14 +632,14 @@ def set_physical_page_for_file(self, pageId, ocrd_file, order=None, orderlabel=N
         if el_seqdiv is None:
             el_seqdiv = ET.SubElement(el_structmap, TAG_METS_DIV)
             el_seqdiv.set('TYPE', 'physSequence')
-        
+
         el_pagediv = None
         if self._cache_flag:
             if pageId in self._page_cache:
                 el_pagediv = self._page_cache[pageId]
         else:
             el_pagediv = el_seqdiv.find('mets:div[@ID="%s"]' % pageId, NS)
-        
+
         if el_pagediv is None:
             el_pagediv = ET.SubElement(el_seqdiv, TAG_METS_DIV)
             el_pagediv.set('TYPE', 'page')
@@ -651,10 +651,10 @@ def set_physical_page_for_file(self, pageId, ocrd_file, order=None, orderlabel=N
             if self._cache_flag:
                 # Create a new entry in the page cache
                 self._page_cache[pageId] = el_pagediv
-                # Create a new entry in the fptr cache and 
+                # Create a new entry in the fptr cache and
                 # assign an empty dictionary to hold the fileids
                 self._fptr_cache[pageId] = {}
-                
+
         el_fptr = ET.SubElement(el_pagediv, TAG_METS_FPTR)
         el_fptr.set('FILEID', ocrd_file.ID)
 
@@ -715,7 +715,7 @@ def remove_physical_page_fptr(self, fileId):
         if self._cache_flag:
             for page_id in self._fptr_cache.keys():
                 if fileId in self._fptr_cache[page_id].keys():
-                    mets_fptrs.append(self._fptr_cache[page_id][fileId]) 
+                    mets_fptrs.append(self._fptr_cache[page_id][fileId])
         else:
             mets_fptrs = self._tree.getroot().xpath(
                 'mets:structMap[@TYPE="PHYSICAL"]/mets:div[@TYPE="physSequence"]/mets:div[@TYPE="page"]/mets:fptr[@FILEID="%s"]' % fileId, namespaces=NS)