Merge pull request #9 from stasm/migrate

Rebase the migration tools from python-l20n

Author: stasm

fluent/migrate/__init__.py

@@ -0,0 +1,8 @@
+# coding=utf8
+
+from .context import MergeContext                      # noqa: F401
+from .transforms import (                              # noqa: F401
+    CONCAT, EXTERNAL, LITERAL, LITERAL_FROM, PLURALS, PLURALS_FROM, REPLACE,
+    REPLACE_FROM, SOURCE
+)
+from .changesets import convert_blame_to_changesets    # noqa: F401

fluent/migrate/changesets.py

@@ -0,0 +1,58 @@
+# coding=utf8
+
+import time
+
+
+def by_first_commit(item):
+    """Order two changesets by their first commit date."""
+    return item['first_commit']
+
+
+def convert_blame_to_changesets(blame_json):
+    """Convert a blame dict into a list of changesets.
+
+    The blame information in `blame_json` should be a dict of the following
+    structure:
+
+        {
+            'authors': [
+                'A.N. Author <author@example.com>',
+            ],
+            'blame': {
+                'path/one': {
+                    'key1': [0, 1346095921.0],
+                },
+            }
+        }
+
+    It will be transformed into a list of changesets which can be fed into
+    `MergeContext.serialize_changeset`:
+
+        [
+            {
+                'author': 'A.N. Author <author@example.com>',
+                'first_commit': 1346095921.0,
+                'changes': {
+                    ('path/one', 'key1'),
+                }
+            },
+        ]
+
+    """
+    now = time.time()
+    changesets = [
+        {
+            'author': author,
+            'first_commit': now,
+            'changes': set()
+        } for author in blame_json['authors']
+    ]
+
+    for path, keys_info in blame_json['blame'].items():
+        for key, (author_index, timestamp) in keys_info.items():
+            changeset = changesets[author_index]
+            changeset['changes'].add((path, key))
+            if timestamp < changeset['first_commit']:
+                changeset['first_commit'] = timestamp
+
+    return sorted(changesets, key=by_first_commit)

fluent/migrate/cldr.py

@@ -0,0 +1,55 @@
+# coding=utf8
+
+import pkgutil
+import json
+
+
+def in_canonical_order(item):
+    return canonical_order.index(item)
+
+
+cldr_plurals = json.loads(
+    pkgutil.get_data('fluent.migrate', 'cldr_data/plurals.json').decode('utf-8')
+)
+
+rules = cldr_plurals['supplemental']['plurals-type-cardinal']
+canonical_order = ('zero', 'one', 'two', 'few', 'many', 'other')
+
+categories = {}
+for lang, rules in rules.items():
+    categories[lang] = tuple(sorted(map(
+        lambda key: key.replace('pluralRule-count-', ''),
+        rules.keys()
+    ), key=in_canonical_order))
+
+
+def get_plural_categories(lang):
+    """Return a tuple of CLDR plural categories for `lang`.
+
+    If an exact match for `lang` is not available, recursively fall back to
+    a language code with the last subtag stripped. That is, if `ja-JP-mac` is
+    not defined in CLDR, the code will try `ja-JP` and then `ja`.
+
+    If no matches are found, a `RuntimeError` is raised.
+
+    >>> get_plural_categories('sl')
+    ('one', 'two', 'few', 'other')
+    >>> get_plural_categories('ga-IE')
+    ('one', 'few', 'two', 'few', 'other')
+    >>> get_plural_categories('ja-JP-mac')
+    ('other')
+
+    """
+
+    langs_categories = categories.get(lang, None)
+
+    if langs_categories is None:
+        # Remove the trailing subtag.
+        fallback_lang, _, _ = lang.rpartition('-')
+
+        if fallback_lang == '':
+            raise RuntimeError('Unknown language: {}'.format(lang))
+
+        return get_plural_categories(fallback_lang)
+
+    return langs_categories

fluent/migrate/cldr_data/plurals.json

@@ -0,0 +1,53 @@
+UNICODE, INC. LICENSE AGREEMENT - DATA FILES AND SOFTWARE
+
+Unicode Data Files include all data files under the directories
+http://www.unicode.org/Public/, http://www.unicode.org/reports/,
+http://www.unicode.org/cldr/data/, http://source.icu-project.org/repos/icu/,
+and http://www.unicode.org/utility/trac/browser/.
+
+Unicode Data Files do not include PDF online code charts under the
+directory http://www.unicode.org/Public/.
+
+Software includes any source code published in the Unicode Standard
+or under the directories
+http://www.unicode.org/Public/, http://www.unicode.org/reports/,
+http://www.unicode.org/cldr/data/, http://source.icu-project.org/repos/icu/,
+and http://www.unicode.org/utility/trac/browser/.
+
+NOTICE TO USER: Carefully read the following legal agreement.
+BY DOWNLOADING, INSTALLING, COPYING OR OTHERWISE USING UNICODE INC.'S DATA
+FILES ("DATA FILES"), AND/OR SOFTWARE ("SOFTWARE"), YOU UNEQUIVOCALLY ACCEPT,
+AND AGREE TO BE BOUND BY, ALL OF THE TERMS AND CONDITIONS OF THIS AGREEMENT.
+IF YOU DO NOT AGREE, DO NOT DOWNLOAD, INSTALL, COPY, DISTRIBUTE OR USE THE
+DATA FILES OR SOFTWARE.
+
+COPYRIGHT AND PERMISSION NOTICE
+
+Copyright © 1991-2016 Unicode, Inc. All rights reserved. Distributed under
+the Terms of Use in http://www.unicode.org/copyright.html.
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of the Unicode data files and any associated documentation (the "Data Files")
+or Unicode software and any associated documentation (the "Software") to deal
+in the Data Files or Software without restriction, including without
+limitation the rights to use, copy, modify, merge, publish, distribute,
+and/or sell copies of the Data Files or Software, and to permit persons to
+whom the Data Files or Software are furnished to do so, provided that either
+(a) this copyright and permission notice appear with all copies of the Data
+Files or Software, or
+(b) this copyright and permission notice appear in associated Documentation.
+
+THE DATA FILES AND SOFTWARE ARE PROVIDED "AS IS", WITHOUT WARRANTY OF ANY
+KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF
+THIRD PARTY RIGHTS. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR HOLDERS
+INCLUDED IN THIS NOTICE BE LIABLE FOR ANY CLAIM, OR ANY SPECIAL INDIRECT OR
+CONSEQUENTIAL DAMAGES, OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE,
+DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER
+TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE
+OF THE DATA FILES OR SOFTWARE.
+
+Except as contained in this notice, the name of a copyright holder shall not
+be used in advertising or otherwise to promote the sale, use or other
+dealings in these Data Files or Software without prior written authorization
+of the copyright holder.