Passed
Pull Request — master (#673)
by Konstantin
02:29
created

ocrd.cli.workspace   F

Complexity

Total Complexity 86

Size/Duplication

Total Lines 601
Duplicated Lines 0 %

Importance

Changes 0
Metric Value
wmc 86
eloc 363
dl 0
loc 601
rs 2
c 0
b 0
f 0

21 Functions

Rating   Name   Duplication   Size   Complexity  
A workspace_remove_file() 0 16 2
B prune_files() 0 28 6
A workspace_backup_add() 0 8 1
A workspace_backup_undo() 0 8 1
A set_id() 0 14 1
A workspace_init() 0 22 2
A remove_group() 0 17 2
A list_pages() 0 8 1
A workspace_backup_list() 0 9 2
A workspace_clone() 0 30 2
A workspace_backup_cli() 0 4 1
A rename_group() 0 11 1
A merge() 0 16 2
A workspace_validate() 0 35 3
A list_groups() 0 8 1
C workspace_find() 0 51 10
A workspace_cli() 0 12 1
F workspace_add_file() 0 51 14
A get_id() 0 10 2
A workspace_backup_restore() 0 10 1
F workspace_cli_bulk_add() 0 93 15

1 Method

Rating   Name   Duplication   Size   Complexity  
F WorkspaceCtx.__init__() 0 25 15

How to fix   Complexity   

Complexity

Complex classes like ocrd.cli.workspace often do a lot of different things. To break such a class down, we need to identify a cohesive component within that class. A common approach to find such a component is to look for fields/methods that share the same prefixes, or suffixes.

Once you have determined the fields that belong together, you can apply the Extract Class refactoring. If the component makes sense as a sub-class, Extract Subclass is also a candidate, and is often faster.

1
import os
2
from os import getcwd
3
from os.path import relpath, exists, join, isabs, dirname, basename, abspath
4
from pathlib import Path
5
from json import loads
6
import sys
7
from glob import glob   # XXX pathlib.Path.glob does not support absolute globs
8
import re
9
10
import click
11
12
from ocrd import Resolver, Workspace, WorkspaceValidator, WorkspaceBackupManager
13
from ocrd_utils import getLogger, initLogging, pushd_popd, EXT_TO_MIME
14
from . import command_with_replaced_help
15
16
17
class WorkspaceCtx():
18
19
    def __init__(self, directory, mets_url, mets_basename, automatic_backup):
20
        self.log = getLogger('ocrd.cli.workspace')
21
        if mets_basename and mets_url:
22
            raise ValueError("Use either --mets or --mets-basename, not both")
23
        if mets_basename and not mets_url:
24
            self.log.warning(DeprecationWarning("--mets-basename is deprecated. Use --mets/--directory instead"))
25
        mets_basename = mets_basename if mets_basename else 'mets.xml'
26
        if directory and mets_url:
27
            directory = abspath(directory)
28
            if not abspath(mets_url).startswith(directory):
29
                raise ValueError("--mets has a directory part inconsistent with --directory")
30
        elif not directory and mets_url:
31
            if mets_url.startswith('http') or mets_url.startswith('https:'):
32
                raise ValueError("--mets is an http(s) URL but no --directory was given")
33
            directory = dirname(abspath(mets_url)) or getcwd()
34
        elif directory and not mets_url:
35
            directory = abspath(directory)
36
            mets_url = join(directory, mets_basename)
37
        else:
38
            directory = getcwd()
39
            mets_url = join(directory, mets_basename)
40
        self.directory = directory
41
        self.resolver = Resolver()
42
        self.mets_url = mets_url
43
        self.automatic_backup = automatic_backup
44
45
pass_workspace = click.make_pass_decorator(WorkspaceCtx)
46
47
# ----------------------------------------------------------------------
48
# ocrd workspace
49
# ----------------------------------------------------------------------
50
51
@click.group("workspace")
52
@click.option('-d', '--directory', envvar='WORKSPACE_DIR', type=click.Path(file_okay=False), metavar='WORKSPACE_DIR', help='Changes the workspace folder location [default: METS_URL directory or .]"')
53
@click.option('-M', '--mets-basename', default=None, help='METS file basename. Deprecated, use --mets/--directory')
54
@click.option('-m', '--mets', default=None, help='The path/URL of the METS file [default: WORKSPACE_DIR/mets.xml]', metavar="METS_URL")
55
@click.option('--backup', default=False, help="Backup mets.xml whenever it is saved.", is_flag=True)
56
@click.pass_context
57
def workspace_cli(ctx, directory, mets, mets_basename, backup):
58
    """
59
    Working with workspace
60
    """
61
    initLogging()
62
    ctx.obj = WorkspaceCtx(directory, mets_url=mets, mets_basename=mets_basename, automatic_backup=backup)
63
64
# ----------------------------------------------------------------------
65
# ocrd workspace validate
66
# ----------------------------------------------------------------------
67
68
@workspace_cli.command('validate', cls=command_with_replaced_help(
69
    (r' \[METS_URL\]', ''))) # XXX deprecated argument
70
@pass_workspace
71
@click.option('-a', '--download', is_flag=True, help="Download all files")
72
@click.option('-s', '--skip', help="Tests to skip", default=[], multiple=True, type=click.Choice(['imagefilename', 'dimension', 'mets_unique_identifier', 'mets_file_group_names', 'mets_files', 'pixel_density', 'page', 'page_xsd', 'mets_xsd', 'url']))
73
@click.option('--page-textequiv-consistency', '--page-strictness', help="How strict to check PAGE multi-level textequiv consistency", type=click.Choice(['strict', 'lax', 'fix', 'off']), default='strict')
74
@click.option('--page-coordinate-consistency', help="How fierce to check PAGE multi-level coordinate consistency", type=click.Choice(['poly', 'baseline', 'both', 'off']), default='poly')
75
@click.argument('mets_url', default=None, required=False)
76
def workspace_validate(ctx, mets_url, download, skip, page_textequiv_consistency, page_coordinate_consistency):
77
    """
78
    Validate a workspace
79
    
80
    METS_URL can be a URL, an absolute path or a path relative to $PWD.
81
    If not given, use --mets accordingly.
82
    
83
    Check that the METS and its referenced file contents
84
    abide by the OCR-D specifications.
85
    """
86
    LOG = getLogger('ocrd.cli.workspace.validate')
87
    if mets_url:
88
        LOG.warning(DeprecationWarning("Use 'ocrd workspace --mets METS init' instead of argument 'METS_URL' ('%s')" % mets_url))
89
    else:
90
        mets_url = ctx.mets_url
91
    report = WorkspaceValidator.validate(
92
        ctx.resolver,
93
        mets_url,
94
        src_dir=ctx.directory,
95
        skip=skip,
96
        download=download,
97
        page_strictness=page_textequiv_consistency,
98
        page_coordinate_consistency=page_coordinate_consistency
99
    )
100
    print(report.to_xml())
101
    if not report.is_valid:
102
        sys.exit(128)
103
104
# ----------------------------------------------------------------------
105
# ocrd workspace clone
106
# ----------------------------------------------------------------------
107
108
@workspace_cli.command('clone', cls=command_with_replaced_help(
109
    (r' \[WORKSPACE_DIR\]', ''))) # XXX deprecated argument
110
@click.option('-f', '--clobber-mets', help="Overwrite existing METS file", default=False, is_flag=True)
111
@click.option('-a', '--download', is_flag=True, help="Download all files and change location in METS file after cloning")
112
@click.argument('mets_url')
113
# XXX deprecated
114
@click.argument('workspace_dir', default=None, required=False)
115
@pass_workspace
116
def workspace_clone(ctx, clobber_mets, download, mets_url, workspace_dir):
117
    """
118
    Create a workspace from METS_URL and return the directory
119
120
    METS_URL can be a URL, an absolute path or a path relative to $PWD.
121
    If METS_URL is not provided, use --mets accordingly.
122
    METS_URL can also be an OAI-PMH GetRecord URL wrapping a METS file.
123
    """
124
    LOG = getLogger('ocrd.cli.workspace.clone')
125
    if workspace_dir:
126
        LOG.warning(DeprecationWarning("Use 'ocrd workspace --directory DIR clone' instead of argument 'WORKSPACE_DIR' ('%s')" % workspace_dir))
127
        ctx.directory = workspace_dir
128
129
    workspace = ctx.resolver.workspace_from_url(
130
        mets_url,
131
        dst_dir=os.path.abspath(ctx.directory),
132
        mets_basename=basename(ctx.mets_url),
133
        clobber_mets=clobber_mets,
134
        download=download,
135
    )
136
    workspace.save_mets()
137
    print(workspace.directory)
138
139
# ----------------------------------------------------------------------
140
# ocrd workspace init
141
# ----------------------------------------------------------------------
142
143
@workspace_cli.command('init', cls=command_with_replaced_help(
144
    (r' \[DIRECTORY\]', ''))) # XXX deprecated argument
145
@click.option('-f', '--clobber-mets', help="Clobber mets.xml if it exists", is_flag=True, default=False)
146
# XXX deprecated
147
@click.argument('directory', default=None, required=False)
148
@pass_workspace
149
def workspace_init(ctx, clobber_mets, directory):
150
    """
151
    Create a workspace with an empty METS file in --directory.
152
153
    """
154
    LOG = getLogger('ocrd.cli.workspace.init')
155
    if directory:
156
        LOG.warning(DeprecationWarning("Use 'ocrd workspace --directory DIR init' instead of argument 'DIRECTORY' ('%s')" % directory))
157
        ctx.directory = directory
158
    workspace = ctx.resolver.workspace_from_nothing(
159
        directory=os.path.abspath(ctx.directory),
160
        mets_basename=basename(ctx.mets_url),
161
        clobber_mets=clobber_mets
162
    )
163
    workspace.save_mets()
164
    print(workspace.directory)
165
166
# ----------------------------------------------------------------------
167
# ocrd workspace add
168
# ----------------------------------------------------------------------
169
170
@workspace_cli.command('add')
171
@click.option('-G', '--file-grp', help="fileGrp USE", required=True, metavar='FILE_GRP')
172
@click.option('-i', '--file-id', help="ID for the file", required=True, metavar='FILE_ID')
173
@click.option('-m', '--mimetype', help="Media type of the file. Guessed from extension if not provided", required=False, metavar='TYPE')
174
@click.option('-g', '--page-id', help="ID of the physical page", metavar='PAGE_ID')
175
@click.option('-C', '--check-file-exists', help="Whether to ensure FNAME exists", is_flag=True, default=False)
176
@click.option('--ignore', help="Do not check whether file exists.", default=False, is_flag=True)
177
@click.option('--force', help="If file with ID already exists, replace it. No effect if --ignore is set.", default=False, is_flag=True)
178
@click.argument('fname', required=True)
179
@pass_workspace
180
def workspace_add_file(ctx, file_grp, file_id, mimetype, page_id, ignore, check_file_exists, force, fname):
181
    """
182
    Add a file or http(s) URL FNAME to METS in a workspace.
183
    If FNAME is not an http(s) URL and is not a workspace-local existing file, try to copy to workspace.
184
    """
185
    workspace = Workspace(ctx.resolver, directory=ctx.directory, mets_basename=basename(ctx.mets_url), automatic_backup=ctx.automatic_backup)
186
187
    log = getLogger('ocrd.cli.workspace.add')
188
    if not mimetype:
189
        try:
190
            mimetype = EXT_TO_MIME[Path(fname).suffix]
191
            log.info("Guessed mimetype to be %s" % mimetype)
192
        except KeyError:
193
            log.error("Cannot guess mimetype from extension '%s' for '%s'. Set --mimetype explicitly" % (Path(fname).suffix, fname))
194
195
    kwargs = {'fileGrp': file_grp, 'ID': file_id, 'mimetype': mimetype, 'pageId': page_id, 'force': force, 'ignore': ignore}
196
    log.debug("Adding '%s' (%s)", fname, kwargs)
197
    if not (fname.startswith('http://') or fname.startswith('https://')):
198
        if not fname.startswith(ctx.directory):
199
            if not isabs(fname) and exists(join(ctx.directory, fname)):
200
                fname = join(ctx.directory, fname)
201
            else:
202
                log.debug("File '%s' is not in workspace, copying", fname)
203
                try:
204
                    fname = ctx.resolver.download_to_directory(ctx.directory, fname, subdir=file_grp)
205
                except FileNotFoundError:
206
                    if check_file_exists:
207
                        log.error("File '%s' does not exist, halt execution!" % fname)
208
                        sys.exit(1)
209
        if check_file_exists and not exists(fname):
210
            log.error("File '%s' does not exist, halt execution!" % fname)
211
            sys.exit(1)
212
        if fname.startswith(ctx.directory):
213
            fname = relpath(fname, ctx.directory)
214
        kwargs['local_filename'] = fname
215
216
    kwargs['url'] = fname
217
    if not page_id:
218
        log.warning("You did not provide '--page-id/-g', so the file you added is not linked to a specific page.")
219
    workspace.mets.add_file(**kwargs)
220
    workspace.save_mets()
221
222
# ----------------------------------------------------------------------
223
# ocrd workspace add-bulk
224
# ----------------------------------------------------------------------
225
226
# pylint: disable=broad-except
227
@workspace_cli.command('bulk-add')
228
@click.option('-r', '--regex', help="Regular expression matching the FILE_GLOB filesystem paths to define named captures usable in the other parameters", required=True)
229
@click.option('-m', '--mimetype', help="Media type of the file. If not provided, guess from filename", required=False)
230
@click.option('-g', '--page-id', help="physical page ID of the file", required=False)
231
@click.option('-i', '--file-id', help="ID of the file", required=True)
232
@click.option('-u', '--url', help="local filesystem path in the workspace directory (copied from source file if different)", required=True)
233
@click.option('-G', '--file-grp', help="File group USE of the file", required=True)
234
@click.option('-n', '--dry-run', help="Don't actually do anything to the METS or filesystem, just preview", default=False, is_flag=True)
235
@click.option('-I', '--ignore', help="Disable checking for existing file entries (faster)", default=False, is_flag=True)
236
@click.option('-f', '--force', help="Replace existing file entries with the same ID (no effect when --ignore is set, too)", default=False, is_flag=True)
237
@click.option('-s', '--skip', help="Skip files not matching --regex (instead of failing)", default=False, is_flag=True)
238
@click.argument('file_glob', nargs=-1, required=True)
239
@pass_workspace
240
def workspace_cli_bulk_add(ctx, regex, mimetype, page_id, file_id, url, file_grp, dry_run, file_glob, ignore, force, skip):
241
    r"""
242
    Add files in bulk to an OCR-D workspace.
243
244
    FILE_GLOB can either be a shell glob expression or a list of files.
245
246
    --regex is applied to the absolute path of every file in FILE_GLOB and can
247
    define named groups that can be used in --page-id, --file-id, --mimetype, --url and
248
    --file-grp by referencing the named group 'grp' in the regex as '{{ grp }}'.
249
250
    \b
251
    Example:
252
        ocrd workspace bulk-add \\
253
                --regex '^.*/(?P<fileGrp>[^/]+)/page_(?P<pageid>.*)\.(?P<ext>[^\.]*)$' \\
254
                --file-id 'FILE_{{ fileGrp }}_{{ pageid }}' \\
255
                --page-id 'PHYS_{{ pageid }}' \\
256
                --file-grp "{{ fileGrp }}" \\
257
                --url '{{ fileGrp }}/FILE_{{ pageid }}.{{ ext }}' \\
258
                path/to/files/*/*.*
259
260
    """
261
    log = getLogger('ocrd.cli.workspace.bulk-add') # pylint: disable=redefined-outer-name
262
    workspace = Workspace(ctx.resolver, directory=ctx.directory, mets_basename=basename(ctx.mets_url), automatic_backup=ctx.automatic_backup)
263
264
    try:
265
        pat = re.compile(regex)
266
    except Exception as e:
267
        log.error("Invalid regex: %s" % e)
268
        sys.exit(1)
269
270
    file_paths = []
271
    for fglob in file_glob:
272
        file_paths += [Path(x).resolve() for x in glob(fglob)]
273
274
    for i, file_path in enumerate(file_paths):
275
        log.info("[%4d/%d] %s" % (i, len(file_paths), file_path))
276
277
        # match regex
278
        m = pat.match(str(file_path))
279
        if not m:
280
            if skip:
281
                continue
282
            log.error("File not matched by regex: '%s'" % file_path)
283
            sys.exit(1)
284
        group_dict = m.groupdict()
285
286
        # set up file info
287
        file_dict = {'url': url, 'mimetype': mimetype, 'ID': file_id, 'pageId': page_id, 'fileGrp': file_grp}
288
289
        # guess mime type
290
        if not file_dict['mimetype']:
291
            try:
292
                file_dict['mimetype'] = EXT_TO_MIME[file_path.suffix]
293
            except KeyError:
294
                log.error("Cannot guess mimetype from extension '%s' for '%s'. Set --mimetype explicitly" % (file_path.suffix, file_path))
295
296
        # expand templates
297
        for param_name in file_dict:
298
            for group_name in group_dict:
299
                file_dict[param_name] = file_dict[param_name].replace('{{ %s }}' % group_name, group_dict[group_name])
300
301
        # copy files
302
        if file_dict['url']:
303
            urlpath = Path(workspace.directory, file_dict['url'])
304
            if not urlpath.exists():
305
                log.info("cp '%s' '%s'", file_path, urlpath)
306
                if not dry_run:
307
                    if not urlpath.parent.is_dir():
308
                        urlpath.parent.mkdir()
309
                    urlpath.write_bytes(file_path.read_bytes())
310
311
        # Add to workspace (or not)
312
        fileGrp = file_dict.pop('fileGrp')
313
        if dry_run:
314
            log.info('workspace.add_file(%s)' % file_dict)
315
        else:
316
            workspace.add_file(fileGrp, ignore=ignore, force=force, **file_dict)
317
318
    # save changes to disk
319
    workspace.save_mets()
320
321
322
# ----------------------------------------------------------------------
323
# ocrd workspace find
324
# ----------------------------------------------------------------------
325
326
@workspace_cli.command('find')
327
@click.option('-G', '--file-grp', help="fileGrp USE", metavar='FILTER')
328
@click.option('-m', '--mimetype', help="Media type to look for", metavar='FILTER')
329
@click.option('-g', '--page-id', help="Page ID", metavar='FILTER')
330
@click.option('-i', '--file-id', help="ID", metavar='FILTER')
331
@click.option('-k', '--output-field', help="Output field. Repeat for multiple fields, will be joined with tab",
332
        default=['url'],
333
        multiple=True,
334
        type=click.Choice([
335
            'url',
336
            'mimetype',
337
            'pageId',
338
            'ID',
339
            'fileGrp',
340
            'basename',
341
            'basename_without_extension',
342
            'local_filename',
343
        ]))
344
@click.option('--download', is_flag=True, help="Download found files to workspace and change location in METS file ")
345
@pass_workspace
346
def workspace_find(ctx, file_grp, mimetype, page_id, file_id, output_field, download):
347
    """
348
    Find files.
349
350
    (If any ``FILTER`` starts with ``//``, then its remainder
351
     will be interpreted as a regular expression.)
352
    """
353
    modified_mets = False
354
    ret = list()
355
    workspace = Workspace(ctx.resolver, directory=ctx.directory, mets_basename=basename(ctx.mets_url))
356
    for f in workspace.mets.find_files(
357
            ID=file_id,
358
            fileGrp=file_grp,
359
            mimetype=mimetype,
360
            pageId=page_id,
361
        ):
362
        if download and not f.local_filename:
363
            workspace.download_file(f)
364
            modified_mets = True
365
        ret.append([f.ID if field == 'pageId' else getattr(f, field) or ''
366
                    for field in output_field])
367
    if modified_mets:
368
        workspace.save_mets()
369
    if 'pageId' in output_field:
370
        idx = output_field.index('pageId')
371
        fileIds = list(map(lambda fields: fields[idx], ret))
0 ignored issues
show
introduced by
The variable idx does not seem to be defined in case 'pageId' in output_field on line 369 is False. Are you sure this can never be the case?
Loading history...
372
        pages = workspace.mets.get_physical_pages(for_fileIds=fileIds)
373
        for fields, page in zip(ret, pages):
374
            fields[idx] = page or ''
375
    for fields in ret:
376
        print('\t'.join(fields))
377
378
# ----------------------------------------------------------------------
379
# ocrd workspace remove
380
# ----------------------------------------------------------------------
381
382
@workspace_cli.command('remove')
383
@click.option('-k', '--keep-file', help="Do not delete file from file system", default=False, is_flag=True)
384
@click.option('-f', '--force', help="Continue even if mets:file or file on file system does not exist", default=False, is_flag=True)
385
@click.argument('ID', nargs=-1)
386
@pass_workspace
387
def workspace_remove_file(ctx, id, force, keep_file):  # pylint: disable=redefined-builtin
388
    """
389
    Delete files (given by their ID attribute ``ID``).
390
    
391
    (If any ``ID`` starts with ``//``, then its remainder
392
     will be interpreted as a regular expression.)
393
    """
394
    workspace = Workspace(ctx.resolver, directory=ctx.directory, mets_basename=basename(ctx.mets_url), automatic_backup=ctx.automatic_backup)
395
    for i in id:
396
        workspace.remove_file(i, force=force, keep_file=keep_file)
397
    workspace.save_mets()
398
399
400
# ----------------------------------------------------------------------
401
# ocrd workspace rename-group
402
# ----------------------------------------------------------------------
403
404
@workspace_cli.command('rename-group')
405
@click.argument('OLD', nargs=1)
406
@click.argument('NEW', nargs=1)
407
@pass_workspace
408
def rename_group(ctx, old, new):
409
    """
410
    Rename fileGrp (USE attribute ``NEW`` to ``OLD``).
411
    """
412
    workspace = Workspace(ctx.resolver, directory=ctx.directory, mets_basename=basename(ctx.mets_url))
413
    workspace.rename_file_group(old, new)
414
    workspace.save_mets()
415
416
# ----------------------------------------------------------------------
417
# ocrd workspace remove-group
418
# ----------------------------------------------------------------------
419
420
@workspace_cli.command('remove-group')
421
@click.option('-r', '--recursive', help="Delete any files in the group before the group itself", default=False, is_flag=True)
422
@click.option('-f', '--force', help="Continue removing even if group or containing files not found in METS", default=False, is_flag=True)
423
@click.option('-k', '--keep-files', help="Do not delete files from file system", default=False, is_flag=True)
424
@click.argument('GROUP', nargs=-1)
425
@pass_workspace
426
def remove_group(ctx, group, recursive, force, keep_files):
427
    """
428
    Delete fileGrps (given by their USE attribute ``GROUP``).
429
    
430
    (If any ``GROUP`` starts with ``//``, then its remainder
431
     will be interpreted as a regular expression.)
432
    """
433
    workspace = Workspace(ctx.resolver, directory=ctx.directory, mets_basename=basename(ctx.mets_url))
434
    for g in group:
435
        workspace.remove_file_group(g, recursive=recursive, force=force, keep_files=keep_files)
436
    workspace.save_mets()
437
438
# ----------------------------------------------------------------------
439
# ocrd workspace prune-files
440
# ----------------------------------------------------------------------
441
442
@workspace_cli.command('prune-files')
443
@click.option('-G', '--file-grp', help="fileGrp USE", metavar='FILTER')
444
@click.option('-m', '--mimetype', help="Media type to look for", metavar='FILTER')
445
@click.option('-g', '--page-id', help="Page ID", metavar='FILTER')
446
@click.option('-i', '--file-id', help="ID", metavar='FILTER')
447
@pass_workspace
448
def prune_files(ctx, file_grp, mimetype, page_id, file_id):
449
    """
450
    Removes mets:files that point to non-existing local files
451
452
    (If any ``FILTER`` starts with ``//``, then its remainder
453
     will be interpreted as a regular expression.)
454
    """
455
    workspace = Workspace(ctx.resolver, directory=ctx.directory, mets_basename=basename(ctx.mets_url), automatic_backup=ctx.automatic_backup)
456
    with pushd_popd(workspace.directory):
457
        for f in workspace.mets.find_files(
458
            ID=file_id,
459
            fileGrp=file_grp,
460
            mimetype=mimetype,
461
            pageId=page_id,
462
        ):
463
            try:
464
                if not f.local_filename or not exists(f.local_filename):
465
                    workspace.mets.remove_file(f.ID)
466
            except Exception as e:
467
                ctx.log.exception("Error removing %f: %s", f, e)
468
                raise(e)
469
        workspace.save_mets()
470
471
# ----------------------------------------------------------------------
472
# ocrd workspace list-group
473
# ----------------------------------------------------------------------
474
475
@workspace_cli.command('list-group')
476
@pass_workspace
477
def list_groups(ctx):
478
    """
479
    List fileGrp USE attributes
480
    """
481
    workspace = Workspace(ctx.resolver, directory=ctx.directory, mets_basename=basename(ctx.mets_url))
482
    print("\n".join(workspace.mets.file_groups))
483
484
# ----------------------------------------------------------------------
485
# ocrd workspace list-pages
486
# ----------------------------------------------------------------------
487
488
@workspace_cli.command('list-page')
489
@pass_workspace
490
def list_pages(ctx):
491
    """
492
    List physical page IDs
493
    """
494
    workspace = Workspace(ctx.resolver, directory=ctx.directory, mets_basename=basename(ctx.mets_url))
495
    print("\n".join(workspace.mets.physical_pages))
496
497
# ----------------------------------------------------------------------
498
# ocrd workspace get-id
499
# ----------------------------------------------------------------------
500
501
@workspace_cli.command('get-id')
502
@pass_workspace
503
def get_id(ctx):
504
    """
505
    Get METS id if any
506
    """
507
    workspace = Workspace(ctx.resolver, directory=ctx.directory, mets_basename=basename(ctx.mets_url))
508
    ID = workspace.mets.unique_identifier
509
    if ID:
510
        print(ID)
511
512
# ----------------------------------------------------------------------
513
# ocrd workspace set-id
514
# ----------------------------------------------------------------------
515
516
@workspace_cli.command('set-id')
517
@click.argument('ID')
518
@pass_workspace
519
def set_id(ctx, id):   # pylint: disable=redefined-builtin
520
    """
521
    Set METS ID.
522
523
    If one of the supported identifier mechanisms is used, will set this identifier.
524
525
    Otherwise will create a new <mods:identifier type="purl">{{ ID }}</mods:identifier>.
526
    """
527
    workspace = Workspace(ctx.resolver, directory=ctx.directory, mets_basename=basename(ctx.mets_url), automatic_backup=ctx.automatic_backup)
528
    workspace.mets.unique_identifier = id
529
    workspace.save_mets()
530
531
# ----------------------------------------------------------------------
532
# ocrd workspace merge
533
# ----------------------------------------------------------------------
534
535
@workspace_cli.command('merge')
536
@click.argument('METS_PATH')
537
@click.option('--copy-files', is_flag=True, help="Copy files as well", default=True)
538
@click.option('--fileGrp-mapping', help="JSON object mapping src to dest fileGrp")
539
@pass_workspace
540
def merge(ctx, copy_files, filegrp_mapping, mets_path):   # pylint: disable=redefined-builtin
541
    """
542
    Merges this workspace with the workspace that contains ``METS_PATH``
543
    """
544
    mets_path = Path(mets_path)
545
    if filegrp_mapping:
546
        filegrp_mapping = loads(filegrp_mapping)
547
    workspace = Workspace(ctx.resolver, directory=ctx.directory, mets_basename=basename(ctx.mets_url), automatic_backup=ctx.automatic_backup)
548
    other_workspace = Workspace(ctx.resolver, directory=str(mets_path.parent), mets_basename=str(mets_path.name))
549
    workspace.merge(other_workspace, copy_files=copy_files, fileGrp_mapping=filegrp_mapping)
550
    workspace.save_mets()
551
552
# ----------------------------------------------------------------------
553
# ocrd workspace backup
554
# ----------------------------------------------------------------------
555
556
@workspace_cli.group('backup')
557
@click.pass_context
558
def workspace_backup_cli(ctx): # pylint: disable=unused-argument
559
    """
560
    Backing and restoring workspaces - dev edition
561
    """
562
563
@workspace_backup_cli.command('add')
564
@pass_workspace
565
def workspace_backup_add(ctx):
566
    """
567
    Create a new backup
568
    """
569
    backup_manager = WorkspaceBackupManager(Workspace(ctx.resolver, directory=ctx.directory, mets_basename=basename(ctx.mets_url), automatic_backup=ctx.automatic_backup))
570
    backup_manager.add()
571
572
@workspace_backup_cli.command('list')
573
@pass_workspace
574
def workspace_backup_list(ctx):
575
    """
576
    List backups
577
    """
578
    backup_manager = WorkspaceBackupManager(Workspace(ctx.resolver, directory=ctx.directory, mets_basename=basename(ctx.mets_url), automatic_backup=ctx.automatic_backup))
579
    for b in backup_manager.list():
580
        print(b)
581
582
@workspace_backup_cli.command('restore')
583
@click.option('-f', '--choose-first', help="Restore first matching version if more than one", is_flag=True)
584
@click.argument('bak') #, type=click.Path(dir_okay=False, readable=True, resolve_path=True))
585
@pass_workspace
586
def workspace_backup_restore(ctx, choose_first, bak):
587
    """
588
    Restore backup BAK
589
    """
590
    backup_manager = WorkspaceBackupManager(Workspace(ctx.resolver, directory=ctx.directory, mets_basename=basename(ctx.mets_url), automatic_backup=ctx.automatic_backup))
591
    backup_manager.restore(bak, choose_first)
592
593
@workspace_backup_cli.command('undo')
594
@pass_workspace
595
def workspace_backup_undo(ctx):
596
    """
597
    Restore the last backup
598
    """
599
    backup_manager = WorkspaceBackupManager(Workspace(ctx.resolver, directory=ctx.directory, mets_basename=basename(ctx.mets_url), automatic_backup=ctx.automatic_backup))
600
    backup_manager.undo()
601