exemplum 1.0.0__tar.gz

exemplum-1.0.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Helmut Konrad Schewe
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS 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. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

exemplum-1.0.0/PKG-INFO

@@ -0,0 +1,20 @@
+Metadata-Version: 2.4
+Name: exemplum
+Version: 1.0.0
+Author-email: Helmut Konrad Schewe <helmutus@outlook.com>
+License-Expression: MIT
+Project-URL: Homepage, https://github.com/anaticulae/pattern
+Project-URL: Repository, https://github.com/anaticulae/pattern
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Requires-Python: >=3.12
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: utilo<3.0.0,>=2.109.1
+Provides-Extra: dev
+Requires-Dist: germania==1.32.0; extra == "dev"
+Requires-Dist: utilotest==1.0.4; extra == "dev"
+Dynamic: license-file
+
+# pattern

exemplum-1.0.0/README

@@ -0,0 +1 @@
+# pattern

exemplum-1.0.0/exemplum.egg-info/PKG-INFO

@@ -0,0 +1,20 @@
+Metadata-Version: 2.4
+Name: exemplum
+Version: 1.0.0
+Author-email: Helmut Konrad Schewe <helmutus@outlook.com>
+License-Expression: MIT
+Project-URL: Homepage, https://github.com/anaticulae/pattern
+Project-URL: Repository, https://github.com/anaticulae/pattern
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Requires-Python: >=3.12
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: utilo<3.0.0,>=2.109.1
+Provides-Extra: dev
+Requires-Dist: germania==1.32.0; extra == "dev"
+Requires-Dist: utilotest==1.0.4; extra == "dev"
+Dynamic: license-file
+
+# pattern

exemplum-1.0.0/exemplum.egg-info/SOURCES.txt

@@ -0,0 +1,31 @@
+LICENSE
+README
+pyproject.toml
+exemplum.egg-info/PKG-INFO
+exemplum.egg-info/SOURCES.txt
+exemplum.egg-info/dependency_links.txt
+exemplum.egg-info/requires.txt
+exemplum.egg-info/top_level.txt
+pattern/__init__.py
+pattern/checker.py
+pattern/split.py
+pattern/tok.py
+pattern/judge/__init__.py
+pattern/judge/abbreviation.py
+pattern/judge/date.py
+pattern/judge/number.py
+pattern/judge/person.py
+pattern/judge/url.py
+pattern/machine/__init__.py
+pattern/machine/machine.py
+pattern/text/__init__.py
+pattern/text/regex.py
+pattern/text/sentence.py
+tests/test_judge_abbreviation.py
+tests/test_judge_date.py
+tests/test_judge_person.py
+tests/test_judge_url.py
+tests/test_machine.py
+tests/test_split.py
+tests/test_text_regex.py
+tests/test_text_sentence.py

exemplum-1.0.0/exemplum.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

exemplum-1.0.0/exemplum.egg-info/requires.txt

@@ -0,0 +1,5 @@
+utilo<3.0.0,>=2.109.1
+
+[dev]
+germania==1.32.0
+utilotest==1.0.4

exemplum-1.0.0/exemplum.egg-info/top_level.txt

@@ -0,0 +1 @@
+pattern

exemplum-1.0.0/pattern/__init__.py

@@ -0,0 +1,22 @@
+#==============================================================================
+# C O P Y R I G H T
+#------------------------------------------------------------------------------
+# Copyright (c) 2019-2020 by Helmut Konrad Fahrendholz. All rights reserved.
+# This file is property of Helmut Konrad Fahrendholz. Any unauthorized copy,
+# use or distribution is an offensive act against international law and may
+# be prosecuted under federal law. Its content is company confidential.
+#==============================================================================
+
+import importlib.metadata
+import os
+
+from pattern.machine.machine import Fixed
+from pattern.machine.machine import Method
+from pattern.machine.machine import PatternMixin
+from pattern.machine.machine import Regex
+from pattern.machine.machine import SimpleCleanup
+from pattern.machine.machine import match
+
+__version__ = importlib.metadata.version('exemplum')
+
+ROOT = os.path.abspath(os.path.join(os.path.dirname(__file__), '..'))

exemplum-1.0.0/pattern/checker.py

@@ -0,0 +1,48 @@
+# =============================================================================
+# C O P Y R I G H T
+# -----------------------------------------------------------------------------
+# Copyright (c) 2020 by Helmut Konrad Fahrendholz. All rights reserved.
+# This file is property of Helmut Konrad Fahrendholz. Any unauthorized copy,
+# use or distribution is an offensive act against international law and may
+# be prosecuted under federal law. Its content is company confidential.
+# =============================================================================
+
+import pattern.judge.abbreviation
+import pattern.judge.date
+import pattern.judge.number
+import pattern.judge.person
+import pattern.judge.url
+import pattern.text.sentence
+
+
+def is_date(item: str) -> float:
+    return pattern.judge.date.validate(item)
+
+
+def is_url(item: str) -> float:
+    return pattern.judge.url.validate(item)
+
+
+def is_person(item: str) -> float:
+    return pattern.judge.person.validate(item)
+
+
+def is_abbreviation(item: str) -> float:
+    return pattern.judge.abbreviation.validate(item)
+
+
+def is_number(item: str) -> float:
+    return pattern.judge.number.validate(item)
+
+
+def is_samesource(item: str) -> float:
+    return pattern.judge.abbreviation.same_source(item)
+
+
+def is_sentence(item: str) -> float:
+    splitted = pattern.text.sentence.split(item)
+    if len(splitted) == 1:
+        splitted = splitted[0]
+        if pattern.text.sentence.is_closed(splitted):
+            return 1.0
+    return 0.0

exemplum-1.0.0/pattern/judge/__init__.py

@@ -0,0 +1,8 @@
+# =============================================================================
+# C O P Y R I G H T
+# -----------------------------------------------------------------------------
+# Copyright (c) 2020 by Helmut Konrad Fahrendholz. All rights reserved.
+# This file is property of Helmut Konrad Fahrendholz. Any unauthorized copy,
+# use or distribution is an offensive act against international law and may
+# be prosecuted under federal law. Its content is company confidential.
+# =============================================================================

exemplum-1.0.0/pattern/judge/abbreviation.py

@@ -0,0 +1,68 @@
+# =============================================================================
+# C O P Y R I G H T
+# -----------------------------------------------------------------------------
+# Copyright (c) 2020 by Helmut Konrad Fahrendholz. All rights reserved.
+# This file is property of Helmut Konrad Fahrendholz. Any unauthorized copy,
+# use or distribution is an offensive act against international law and may
+# be prosecuted under federal law. Its content is company confidential.
+# =============================================================================
+
+
+def validate(item: str) -> float:
+    item = item.lower()
+    result = max((strategy(item) for strategy in (dictionary,)))
+    return result
+
+
+def dictionary(item):
+    if item not in ABBREVIATION:
+        return 0.0
+    return 1.0
+
+
+def same_source(item) -> float:
+    if item in SAME_SOURCE:
+        return 5.0
+    return 0.0
+
+
+ABBREVIATION = {
+    'Aufl.',
+    'Bd.',
+    'Co.',
+    'Diss.',
+    'Dok.',
+    'Forts.',
+    'Hrsg.',
+    'Jg.',
+    'Sp.',
+    'Verf.',
+    'Verl.',
+    'Vol.',
+    'a.a.O.',
+    'al.',
+    'bzw.',
+    'ebd.',
+    'ebd.:',
+    'et al',
+    'etc.',
+    'ff.'
+    'ggf.',
+    'lat.',
+    'mind.',
+    'o.A.',
+    'o.J.',
+    'o.V.',
+    'o.Ä',
+    's.',
+    'usw.',
+    'vgl.',
+    'z.B.',
+}
+
+ABBREVIATION = {item.lower() for item in ABBREVIATION}
+
+SAME_SOURCE = {
+    'ebd.',
+    'ebd.:',
+}

exemplum-1.0.0/pattern/judge/date.py

@@ -0,0 +1,83 @@
+# =============================================================================
+# C O P Y R I G H T
+# -----------------------------------------------------------------------------
+# Copyright (c) 2020 by Helmut Konrad Fahrendholz. All rights reserved.
+# This file is property of Helmut Konrad Fahrendholz. Any unauthorized copy,
+# use or distribution is an offensive act against international law and may
+# be prosecuted under federal law. Its content is company confidential.
+# =============================================================================
+
+import utilo
+
+
+@utilo.cacheme
+def validate(item: str) -> float:
+    result = [
+        strategy(item) for strategy in (
+            day_month_year,
+            day_name_year,
+            no_date,
+        )
+    ]
+    return max(result)
+
+
+DATE_FACTOR = 5.0
+
+DAY_MONTH_YEAR = utilo.compiles(r"""
+    (?P<day>\d{1,2})
+    \.
+    (?P<month>\d{1,2})
+    \.
+    (?P<year>(20[012]\d|1[789]\d\d))
+""")
+
+
+@utilo.cacheme
+def day_month_year(item: str):
+    """\
+    >>> day_month_year('25.08.1987')
+    5.0
+    """
+    matched = DAY_MONTH_YEAR.match(item)
+    if not matched:
+        return 0.0
+    day = int(matched['day'])
+    month = int(matched['month'])
+    year = int(matched['year'])
+    if not 1 <= day <= 31:
+        return 0.0
+    if not 1 <= month <= 12:
+        return 0.0
+    if not 1700 <= year <= 2030:
+        return 0.0
+    return DATE_FACTOR
+
+
+DAY_NAME_YEAR = utilo.compiles(r"""
+    (?P<day>\d{1,2})\.[ ]{0,1}
+    (?P<month>Januar|Februar|März|April|Mai|Juni|Juli|
+              August|September|Oktober|November|Dezember
+    )
+    [ ]{0,1}
+    (?P<year>(20[012]\d|1[789]\d\d))
+""")
+
+
+@utilo.cacheme
+def day_name_year(item: str) -> float:
+    """\
+    >>> day_name_year('20. April 1999')
+    5.0
+    >>> day_name_year('01. Januar 1733')
+    5.0
+    """
+    if DAY_NAME_YEAR.match(item):
+        return DATE_FACTOR
+    return 0.0
+
+
+def no_date(item: str):
+    if item != 'o.J.':
+        return 0.0
+    return DATE_FACTOR

exemplum-1.0.0/pattern/judge/number.py

@@ -0,0 +1,16 @@
+# =============================================================================
+# C O P Y R I G H T
+# -----------------------------------------------------------------------------
+# Copyright (c) 2020 by Helmut Konrad Fahrendholz. All rights reserved.
+# This file is property of Helmut Konrad Fahrendholz. Any unauthorized copy,
+# use or distribution is an offensive act against international law and may
+# be prosecuted under federal law. Its content is company confidential.
+# =============================================================================
+
+
+def validate(item: str) -> float:
+    try:
+        int(item)
+    except ValueError:
+        return 0.0
+    return 1.0

exemplum-1.0.0/pattern/judge/person.py

@@ -0,0 +1,44 @@
+# =============================================================================
+# C O P Y R I G H T
+# -----------------------------------------------------------------------------
+# Copyright (c) 2020 by Helmut Konrad Fahrendholz. All rights reserved.
+# This file is property of Helmut Konrad Fahrendholz. Any unauthorized copy,
+# use or distribution is an offensive act against international law and may
+# be prosecuted under federal law. Its content is company confidential.
+# =============================================================================
+
+
+def validate(item: str) -> float:
+    result = max((strategy(item) for strategy in (dictionary,)))
+    return result
+
+
+def dictionary(item):
+    splitted = item.split(' ')
+    for name in splitted:
+        if all([
+                name not in SURNAME,
+                name not in NAME,
+                name != 'von',
+        ]):
+            return 0.0
+    # prefere person over abbreviation
+    return 5.0
+
+
+# TODO: LOAD FROM FILE
+
+SURNAME = {
+    'Angela',
+    'Frank',
+    'Gero',
+    'Martin',
+}
+
+NAME = {
+    'Gatterburg',
+    'Hornig',
+    'Randow',
+    'Simons',
+    'o.A.',
+}

exemplum-1.0.0/pattern/judge/url.py

@@ -0,0 +1,27 @@
+# =============================================================================
+# C O P Y R I G H T
+# -----------------------------------------------------------------------------
+# Copyright (c) 2020 by Helmut Konrad Fahrendholz. All rights reserved.
+# This file is property of Helmut Konrad Fahrendholz. Any unauthorized copy,
+# use or distribution is an offensive act against international law and may
+# be prosecuted under federal law. Its content is company confidential.
+# =============================================================================
+
+import urllib.parse
+
+
+def validate(item: str) -> float:
+    result = [strategy(item) for strategy in (urllib_parse,)]
+    return max(result)
+
+
+def urllib_parse(item):
+    # TODO: check this
+    if '.' not in item:
+        return 0.0
+    if ',' in item:
+        return 0.0
+    parsed = urllib.parse.urlparse(item)
+    if not parsed:
+        return 0.0
+    return 1.0

exemplum-1.0.0/pattern/machine/__init__.py

@@ -0,0 +1,8 @@
+# =============================================================================
+# C O P Y R I G H T
+# -----------------------------------------------------------------------------
+# Copyright (c) 2021 by Helmut Konrad Fahrendholz. All rights reserved.
+# This file is property of Helmut Konrad Fahrendholz. Any unauthorized copy,
+# use or distribution is an offensive act against international law and may
+# be prosecuted under federal law. Its content is company confidential.
+# =============================================================================

exemplum-1.0.0/pattern/machine/machine.py

@@ -0,0 +1,114 @@
+# =============================================================================
+# C O P Y R I G H T
+# -----------------------------------------------------------------------------
+# Copyright (c) 2021 by Helmut Konrad Fahrendholz. All rights reserved.
+# This file is property of Helmut Konrad Fahrendholz. Any unauthorized copy,
+# use or distribution is an offensive act against international law and may
+# be prosecuted under federal law. Its content is company confidential.
+# =============================================================================
+"""\
+    Bill Nitzberg und Virginia Lo. Distributed Shared Memory: A Survey
+    of Issue and Algorithms. In: Computer 24.8 (Aug. 1991), S. 52-60.
+    issn: 0018-9162. doi: 10. 1109/2.84877. url:
+    http://dx.doi.org/10.1109/2.84877.
+"""
+
+import functools
+import re
+
+import utilo
+
+
+def match(text: str, patterns: list, improves: list = None) -> dict:
+    replaced = text
+    # prepare data
+    if improves:
+        for improve in improves:
+            replaced = improve(replaced)
+    # collect pattern
+    patterns = prepare(patterns)
+    collected = {}
+    for pattern in patterns:
+        matched = pattern(replaced)
+        if not matched:
+            continue
+        before = matched
+        if isinstance(matched, str):
+            matched = [matched]
+        for raw in matched:
+            if not isinstance(raw, str):
+                raw = raw[1]
+            replaced = replaced.replace(raw, '*' * len(raw))
+        if pattern.store:
+            if pattern.overwrite or pattern.name not in collected:
+                collected[pattern.name] = before
+    result = {
+        "text": text,
+        "replaced": replaced,
+        "data": collected,
+    }
+    return result
+
+
+class PatternMixin:
+
+    def __init__(self, name: str):
+        self.name = name
+        self.store = True
+        self.overwrite = False
+
+
+class Fixed(PatternMixin):
+
+    def __init__(self, const: str):
+        super().__init__(name=const.lower())
+        self.const = const
+        self.store = False
+
+    def __call__(self, text):
+        return re.findall(self.const, text, utilo.NOCASE_VERBOSE)
+
+
+class Regex(Fixed):
+
+    def __init__(self, regex: str, name: str):
+        super().__init__(const=regex)
+        self.name = name.lower()
+        self.store = True
+
+
+class SimpleCleanup(Fixed):
+
+    def __init__(self):
+        super().__init__('cleanup')
+        self.const = r'(\*\s{1,}\*|\(\*{1,}\)|\*\,\s{1,}\*|\*\.\s{1,}\*)'
+        self.store = False
+
+
+class Method(PatternMixin):
+
+    def __init__(self, method: callable):
+        super().__init__(name=method.__name__.lower())
+        self.verbose = 'verbose' in utilo.attributes(method)
+        if self.verbose:
+            method = functools.partial(method, verbose=True)
+        self.method = method
+
+    def __call__(self, text):
+        result = self.method(text)
+        return result
+
+
+def prepare(patterns: list):
+    result = []
+    for pattern in patterns:
+        isclass = str(pattern.__class__) == "<class 'type'>"
+        if isinstance(pattern, str):
+            result.append(Fixed(const=pattern))
+        elif isinstance(pattern, PatternMixin):
+            result.append(pattern)
+        elif isclass:
+            result.append(pattern())
+        elif callable(pattern):
+            result.append(Method(pattern))
+    return result

exemplum-1.0.0/pattern/split.py

@@ -0,0 +1,62 @@
+# =============================================================================
+# C O P Y R I G H T
+# -----------------------------------------------------------------------------
+# Copyright (c) 2020 by Helmut Konrad Fahrendholz. All rights reserved.
+# This file is property of Helmut Konrad Fahrendholz. Any unauthorized copy,
+# use or distribution is an offensive act against international law and may
+# be prosecuted under federal law. Its content is company confidential.
+# =============================================================================
+
+import pattern.checker
+import pattern.tok
+
+STRATEGY = [
+    (pattern.tok.Token.ABBREVIATION, pattern.checker.is_abbreviation),
+    (pattern.tok.Token.DATE, pattern.checker.is_date),
+    (pattern.tok.Token.PAGE, pattern.checker.is_number),
+    (pattern.tok.Token.PERSON, pattern.checker.is_person),
+    (pattern.tok.Token.SAME_SOURCE, pattern.checker.is_samesource),
+    (pattern.tok.Token.URL, pattern.checker.is_url),
+]
+
+
+def split(line: str):
+    comma = ',' in line
+    result = []
+
+    splitted = tokenize(line)
+    for token in splitted:
+        token = token.strip()
+        result.append(analyze(token))
+
+    if comma:
+        items = []
+        for item in result:
+            items.append(item)
+            items.append(pattern.tok.Token.COMMA)
+        result = items[:-1]  # remove last comma token
+    return result
+
+
+def tokenize(line: str):
+    if ',' in line:
+        splitted = line.split(',')
+    else:
+        splitted = line.split()
+    return splitted
+
+
+def analyze(token: str) -> pattern.tok.Token:
+    result = [strategy(token) for _, strategy in STRATEGY]
+    index = max_index(result)
+    return STRATEGY[index][0]
+
+
+def max_index(items) -> int:
+    result, value = 0, items[0]
+    for index, item in enumerate(items[1:], start=1):
+        if item <= value:
+            continue
+        value = item
+        result = index
+    return result

exemplum-1.0.0/pattern/text/__init__.py

@@ -0,0 +1,8 @@
+# =============================================================================
+# C O P Y R I G H T
+# -----------------------------------------------------------------------------
+# Copyright (c) 2020 by Helmut Konrad Fahrendholz. All rights reserved.
+# This file is property of Helmut Konrad Fahrendholz. Any unauthorized copy,
+# use or distribution is an offensive act against international law and may
+# be prosecuted under federal law. Its content is company confidential.
+# =============================================================================

exemplum-1.0.0/pattern/text/regex.py

@@ -0,0 +1,41 @@
+# =============================================================================
+# C O P Y R I G H T
+# -----------------------------------------------------------------------------
+# Copyright (c) 2020 by Helmut Konrad Fahrendholz. All rights reserved.
+# This file is property of Helmut Konrad Fahrendholz. Any unauthorized copy,
+# use or distribution is an offensive act against international law and may
+# be prosecuted under federal law. Its content is company confidential.
+# =============================================================================
+
+
+def user(
+    parameter='text',
+    greedy: bool = True,
+    newlines: bool = False,
+    limit=None,
+):
+    if limit is None:
+        limit = (1, None)
+    ranges = '{%s,%s}' % (limit[0], limit[1] if limit[1] is not None else '')
+    greedy = '' if greedy else '?'
+    newlines = r'[\n]|' if newlines else ''
+    pattern =\
+        ('('
+         f'?P<{parameter}>'
+         r'('
+         r'[\w\d]|'
+         r'[ ]|'
+         f'{newlines}'
+         r'[=\(\)\[\]{}\<\>]|'
+         r'[,;:\.?!]|'
+         r'[~`]|'
+         r'[@#$%^&*\-_+]|'
+         r'[\'\"]|'
+         r'[’„“]|'
+         r'[–]' # special minus sign
+         r')'
+         f'{ranges}'
+         f'{greedy}'
+         r')'
+        )
+    return pattern

exemplum-1.0.0/pattern/text/sentence.py

@@ -0,0 +1,71 @@
+# =============================================================================
+# C O P Y R I G H T
+# -----------------------------------------------------------------------------
+# Copyright (c) 2020 by Helmut Konrad Fahrendholz. All rights reserved.
+# This file is property of Helmut Konrad Fahrendholz. Any unauthorized copy,
+# use or distribution is an offensive act against international law and may
+# be prosecuted under federal law. Its content is company confidential.
+# =============================================================================
+
+import contextlib
+
+import pattern.checker
+
+
+def split(text: str) -> list[str]:
+    """Split a regular `text` into sentence chunks.
+
+    Args:
+        text(str): text to split without any newlines
+    Returns:
+        list of splitted sentences
+    """
+    # TODO: REPLACE WITH EXTERNAL SMART ALTERNATIVE, facebook, google or
+    # something else.
+    result = []
+    current = []
+    tokens = text.split(' ')
+    for token in tokens:
+        if not token:
+            continue
+        current.append(token)
+        token = token.lower()  # make approach more robust
+        lastchar = token[-1]
+        if lastchar == '.':
+            if len(token) == 2:
+                # W. or G.
+                continue
+            if pattern.checker.is_abbreviation(token):
+                continue
+            if token[:-1].isnumeric():
+                # 1.; 13.
+                continue
+            if token.startswith('('):
+                # (z.B.)
+                continue
+        if lastchar in SIGN:
+            result.append(' '.join(current))
+            current = []
+    if current:
+        result.append(' '.join(current))
+    return result
+
+
+def is_closed(token: list) -> bool:
+    """Check that the last character of the last token of a sentences
+    contains a sentence close sign."""
+    with contextlib.suppress(AttributeError):
+        # support str as input
+        token = token.split()
+    assert token, 'empty sentence'
+    last = token[-1].strip()
+    last_char = last[-1]
+    return last_char in SIGN
+
+
+SIGN = {
+    '!',
+    '.',
+    ':',
+    '?',
+}

exemplum-1.0.0/pattern/tok.py

@@ -0,0 +1,20 @@
+# =============================================================================
+# C O P Y R I G H T
+# -----------------------------------------------------------------------------
+# Copyright (c) 2020 by Helmut Konrad Fahrendholz. All rights reserved.
+# This file is property of Helmut Konrad Fahrendholz. Any unauthorized copy,
+# use or distribution is an offensive act against international law and may
+# be prosecuted under federal law. Its content is company confidential.
+# =============================================================================
+
+import enum
+
+
+class Token(enum.Enum):
+    ABBREVIATION = enum.auto()
+    COMMA = enum.auto()
+    DATE = enum.auto()
+    PAGE = enum.auto()
+    PERSON = enum.auto()
+    SAME_SOURCE = enum.auto()
+    URL = enum.auto()

exemplum-1.0.0/pyproject.toml

@@ -0,0 +1,85 @@
+[build-system]
+requires = [
+    "setuptools>=83.0.0",
+    "wheel>=0.47.0",
+]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "exemplum"
+version = "1.0.0"
+description = ""
+requires-python = ">=3.12"
+authors = [
+    { name = "Helmut Konrad Schewe", email = "helmutus@outlook.com" },
+]
+dependencies = [
+    "utilo>=2.109.1,<3.0.0",
+]
+keywords = []
+classifiers = [
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
+    "Programming Language :: Python :: 3.14",
+]
+license = "MIT"
+license-files = [
+    "LICENSE",
+]
+
+[project.readme]
+file = "README"
+content-type = "text/markdown"
+
+[project.optional-dependencies]
+dev = [
+    "germania==1.32.0",
+    "utilotest==1.0.4",
+]
+
+[project.urls]
+Homepage = "https://github.com/anaticulae/pattern"
+Repository = "https://github.com/anaticulae/pattern"
+
+[tool.semantic_release]
+version_toml = [
+    "pyproject.toml:project.version",
+]
+
+[tool.semantic_release.changelog]
+mode = "init"
+output_format = "md"
+
+[tool.semantic_release.changelog.default_templates]
+changelog_file = "CHANGELOG"
+
+[tool.semantic_release.commit_parser_options]
+patch_tags = [
+    "build",
+    "chore",
+    "ci",
+    "deps",
+    "docs",
+    "fix",
+    "perf",
+    "refactor",
+    "style",
+    "test",
+]
+minor_tags = [
+    "feat",
+]
+
+[tool.setuptools.packages.find]
+where = [
+    ".",
+]
+include = [
+    "pattern",
+    "pattern.judge",
+    "pattern.machine",
+    "pattern.text",
+]
+exclude = [
+    "tests*",
+]

exemplum-1.0.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

exemplum-1.0.0/tests/test_judge_abbreviation.py

@@ -0,0 +1,35 @@
+# =============================================================================
+# C O P Y R I G H T
+# -----------------------------------------------------------------------------
+# Copyright (c) 2020 by Helmut Konrad Fahrendholz. All rights reserved.
+# This file is property of Helmut Konrad Fahrendholz. Any unauthorized copy,
+# use or distribution is an offensive act against international law and may
+# be prosecuted under federal law. Its content is company confidential.
+# =============================================================================
+
+import pytest
+
+import pattern.checker
+
+
+@pytest.mark.parametrize(
+    'item',
+    [
+        'ebd.',
+        'o.J.',  # handled by date
+        'o.A.',  # handled by person
+    ])
+def test_is_abbreviation_valid(item):
+    valid = pattern.checker.is_abbreviation(item)
+    assert valid >= 1.0, item
+
+
+@pytest.mark.parametrize(
+    'item',
+    [
+        'Hallo',
+    ],
+)
+def test_is_abbreviation_invalid(item):
+    valid = pattern.checker.is_abbreviation(item)
+    assert not valid, item

exemplum-1.0.0/tests/test_judge_date.py

@@ -0,0 +1,28 @@
+# =============================================================================
+# C O P Y R I G H T
+# -----------------------------------------------------------------------------
+# Copyright (c) 2020 by Helmut Konrad Fahrendholz. All rights reserved.
+# This file is property of Helmut Konrad Fahrendholz. Any unauthorized copy,
+# use or distribution is an offensive act against international law and may
+# be prosecuted under federal law. Its content is company confidential.
+# =============================================================================
+import pytest
+
+import pattern.checker
+
+
+@pytest.mark.parametrize('item', [
+    '20.10.2020',
+    '20. Oktober 2020',
+])
+def test_is_date_valid(item):
+    valid = pattern.checker.is_date(item)
+    assert valid >= 1.0, item
+
+
+@pytest.mark.parametrize('item', [
+    '40.10.2020',
+])
+def test_is_date_invalid(item):
+    valid = pattern.checker.is_date(item)
+    assert not valid, item

exemplum-1.0.0/tests/test_judge_person.py

@@ -0,0 +1,23 @@
+# =============================================================================
+# C O P Y R I G H T
+# -----------------------------------------------------------------------------
+# Copyright (c) 2020 by Helmut Konrad Fahrendholz. All rights reserved.
+# This file is property of Helmut Konrad Fahrendholz. Any unauthorized copy,
+# use or distribution is an offensive act against international law and may
+# be prosecuted under federal law. Its content is company confidential.
+# =============================================================================
+
+import pytest
+
+import pattern.checker
+
+
+@pytest.mark.parametrize('item', [
+    'Angela Gatterburg',
+    'Frank Hornig',
+    'Gero von Randow',
+    'Martin Simons',
+])
+def test_is_person_valid(item):
+    valid = pattern.checker.is_person(item)
+    assert valid >= 1.0, item

exemplum-1.0.0/tests/test_judge_url.py

@@ -0,0 +1,34 @@
+# =============================================================================
+# C O P Y R I G H T
+# -----------------------------------------------------------------------------
+# Copyright (c) 2020 by Helmut Konrad Fahrendholz. All rights reserved.
+# This file is property of Helmut Konrad Fahrendholz. Any unauthorized copy,
+# use or distribution is an offensive act against international law and may
+# be prosecuted under federal law. Its content is company confidential.
+# =============================================================================
+
+import pytest
+
+import pattern.checker
+
+
+@pytest.mark.parametrize('item', [
+    'spiegel.de',
+    pytest.param(
+        ('http://classiques.uqac.ca/classiques/Halbwachs_maurice/'
+         'memoire_collective/memoire_collective.pdf'),
+        id='uqac.ca',
+    ),
+])
+def test_is_url_valid(item):
+    valid = pattern.checker.is_url(item)
+    assert valid >= 1.0, item
+
+
+@pytest.mark.parametrize('item', [
+    'spiegel-de',
+    'http://info.spiegel,de',
+])
+def test_is_url_invalid(item):
+    valid = pattern.checker.is_url(item)
+    assert not valid, item

exemplum-1.0.0/tests/test_machine.py

@@ -0,0 +1,120 @@
+# =============================================================================
+# C O P Y R I G H T
+# -----------------------------------------------------------------------------
+# Copyright (c) 2021 by Helmut Konrad Fahrendholz. All rights reserved.
+# This file is property of Helmut Konrad Fahrendholz. Any unauthorized copy,
+# use or distribution is an offensive act against international law and may
+# be prosecuted under federal law. Its content is company confidential.
+# =============================================================================
+
+import germania
+import utilo
+
+import pattern
+
+RAW = """Bill Nitzberg und Virginia Lo. Distributed Shared Memory: A
+Survey of Issue and Algorithms. In: Computer 24.8 (Aug. 1991), S. 52-60.
+issn: 0018-9162. doi: 10. 1109/2.84877. url:
+http://dx.doi.org/10.1109/2.84877.
+"""
+
+URL = 'URL:'
+IN = r'IN:[^\*]+'
+
+PATTERN = (
+    germania.issn,
+    germania.isbn,
+    germania.doi,
+    germania.pagenumbers,
+    germania.hyperlink,
+    germania.dates_master,
+    URL,
+    pattern.SimpleCleanup,
+    pattern.Regex(regex=IN, name='in-pattern'),
+    pattern.SimpleCleanup,
+)
+
+IMPROVES = (germania.href_magic,)
+
+
+def test_machine_simple():
+    matched = pattern.match(
+        RAW,
+        patterns=PATTERN,
+        improves=IMPROVES,
+    )
+    replaced = matched['replaced']
+    assert 'url' not in replaced
+    assert replaced.count('*') >= 82
+    values = list(matched['data'].keys())
+    assert values == [
+        'issn', 'doi', 'pagenumbers', 'hyperlink', 'dates_master', 'in-pattern'
+    ]
+
+
+class SmartAuthor(pattern.PatternMixin):
+
+    def __init__(self):
+        super().__init__('authors')
+
+    def __call__(self, text):
+        first_star = text.find('*')
+        if first_star != -1:
+            text = text[0:first_star]
+        words = text.split()
+        valid = [item for item in words if germania.isperson(item)]
+        if not valid:
+            return []
+        last_author = text.rfind(valid[-1]) + len(valid[-1])
+        authors = text[0:last_author]
+        return authors
+
+
+SMART = list(PATTERN) + [SmartAuthor]
+
+
+def test_machine_smart_author():
+    matched = pattern.match(
+        RAW,
+        patterns=SMART,
+        improves=IMPROVES,
+    )
+    expected = 'Bill Nitzberg und Virginia'
+    assert matched['data']['authors'] == expected
+
+
+TITLE = """Michael Armbrust u.a. “Spark SQL: Relational Data Processing
+in Spark”. In: Proceedings of the 2015 ACM SIGMOD International
+Conference on Management of Data.SIGMOD’ 15. Melbourne, Victoria,
+Australia:ACM, 2015, S.1383–1394. isbn:978-1-4503-2758-9. doi:
+10.1145/2723372.2742797.url: http://doi.acm.org/10.1145/2723372.2742797.
+"""
+
+
+class Titles(pattern.PatternMixin):
+
+    QUOTATIONS = '“”'
+
+    def __init__(self):
+        super().__init__('titles')
+
+    def __call__(self, text):
+        indexs = utilo.findindexs(text, Titles.QUOTATIONS)
+        if not indexs:
+            return []
+        start, stop = min(indexs), max(indexs)
+        result = text[start:stop + 1]
+        return result
+
+
+TITLES = list(PATTERN) + [Titles]
+
+
+def test_machine_title():
+    matched = pattern.match(
+        TITLE,
+        patterns=TITLES,
+        improves=IMPROVES,
+    )
+    titles = matched['data']['titles']
+    assert titles == '“Spark SQL: Relational Data Processing\nin Spark”'

exemplum-1.0.0/tests/test_split.py

@@ -0,0 +1,48 @@
+# =============================================================================
+# C O P Y R I G H T
+# -----------------------------------------------------------------------------
+# Copyright (c) 2020 by Helmut Konrad Fahrendholz. All rights reserved.
+# This file is property of Helmut Konrad Fahrendholz. Any unauthorized copy,
+# use or distribution is an offensive act against international law and may
+# be prosecuted under federal law. Its content is company confidential.
+# =============================================================================
+import pytest
+
+import pattern.split
+
+EXAMPLE = """\
+Angela Gatterburg, spiegel.de, 21.4.2009
+Martin Simons, welt.de, 26.10.2009
+Frank Hornig, spiegel.de, 17.7.2006
+o.A., bild.de, o.J.
+o.A., computerwoche.de, 23.1.2008
+"""
+
+
+@pytest.mark.parametrize('line', EXAMPLE.splitlines())
+def test_split_person_url_date(line):
+    splitted = pattern.split.split(line)
+    expected = [
+        pattern.tok.Token.PERSON,
+        pattern.tok.Token.COMMA,
+        pattern.tok.Token.URL,
+        pattern.tok.Token.COMMA,
+        pattern.tok.Token.DATE,
+    ]
+    assert splitted == expected, str(splitted)
+
+
+MORE = """\
+s. ebd.: 126
+"""
+
+
+@pytest.mark.parametrize('line', MORE.splitlines())
+def test_abbreviation_autor_page(line):
+    splitted = pattern.split.split(line)
+    expected = [
+        pattern.tok.Token.ABBREVIATION,
+        pattern.tok.Token.SAME_SOURCE,
+        pattern.tok.Token.PAGE,
+    ]
+    assert splitted == expected, str(splitted)

exemplum-1.0.0/tests/test_text_regex.py

@@ -0,0 +1,28 @@
+# =============================================================================
+# C O P Y R I G H T
+# -----------------------------------------------------------------------------
+# Copyright (c) 2020 by Helmut Konrad Fahrendholz. All rights reserved.
+# This file is property of Helmut Konrad Fahrendholz. Any unauthorized copy,
+# use or distribution is an offensive act against international law and may
+# be prosecuted under federal law. Its content is company confidential.
+# =============================================================================
+
+import re
+
+import pytest
+
+import pattern.text.regex
+
+
+@pytest.mark.parametrize('text', [
+    'Hello',
+    '123 Hello',
+    pytest.param('Programm Code hello(item,){a=[10];}', id='program code'),
+    '!@#$%^&*()-_=+',
+    'Hello c’est „Hello“',
+])
+def test_text_regex_user(text):
+    regex = pattern.text.regex.user()
+    matched = re.match(regex, text)
+    assert matched
+    assert matched['text'] == text, matched

exemplum-1.0.0/tests/test_text_sentence.py

@@ -0,0 +1,53 @@
+# =============================================================================
+# C O P Y R I G H T
+# -----------------------------------------------------------------------------
+# Copyright (c) 2020 by Helmut Konrad Fahrendholz. All rights reserved.
+# This file is property of Helmut Konrad Fahrendholz. Any unauthorized copy,
+# use or distribution is an offensive act against international law and may
+# be prosecuted under federal law. Its content is company confidential.
+# =============================================================================
+
+import pytest
+
+import pattern.checker
+import pattern.text.sentence
+
+PARAGRAPH = """\
+boyd nutzt in diesem Zusammenhang den Begriff Networked Publics, der
+allerdings nicht immer klar von Public im Sinne von Öffentlichkeit
+abgegrenzt wird. Daher wird er in der vorliegenden Arbeit nicht
+verwendet. Die von boyd aufgeführten Eigenschaften werden stattdessen
+unter der Bezeichnung „netzbasierte Kommunikation“ zusammengefasst.
+"""
+
+SINGLE = """\
+Aus Gründen der besseren Lesbarkeit wird hier und im Folgenden
+ausschließlich die maskuline Form verwendet, wobei immer beide
+Geschlechter gemeint sind.
+"""
+
+NO_SENTENCE = 'This is not a sentence'
+
+
+@pytest.mark.parametrize('text, sentences', [
+    pytest.param(PARAGRAPH, 3, id='three_sentences'),
+    pytest.param(SINGLE, 1, id='single_sentences'),
+])
+def test_text_sentence_split(text, sentences):
+    splitted = pattern.text.sentence.split(text)
+    assert len(splitted) == sentences, splitted
+
+
+@pytest.mark.parametrize('line', [
+    pytest.param(SINGLE, id='single_sentences'),
+])
+def test_text_sentence_issentence(line):
+    assert pattern.checker.is_sentence(line), line
+
+
+@pytest.mark.parametrize('line', [
+    pytest.param(PARAGRAPH, id='three_sentences'),
+    pytest.param(NO_SENTENCE, id='no_sentence'),
+])
+def test_text_sentence_issentence_invalid(line):
+    assert not pattern.checker.is_sentence(line), line