invesytoolbox 0.0.22__tar.gz → 0.0.23__tar.gz

{invesytoolbox-0.0.22 → invesytoolbox-0.0.23}/HISTORY.md

@@ -1,4 +1,13 @@
 # History
+## 0.0.23 (2024-07-22)
+* **adjust_spaces_on_punctuation**: inserts narrow (or normal spaces) for certain languages
+* **value_2datatype**: 
+  - default fmt changed to None (hopefully it doesn't break somewhere, but this is necessary)
+  - 'pendulum' is now an option for the parameter 
+- default for parameter **fmt** changed to None (this is necessary for the new pendulum conversion in **value_2datatype** to work) for
+	- **dict_2datatypes**
+	- **dictlist_2datatypes**
+
 ## 0.0.22 (2023-10-14)
 * **normalize_name** and **could_be_a_name** now have the boolean parameter *lastname* that indicates that a single-word name is to be treated as a last name, not a first name.
 * **get_locale**: locale can be only the language, without the country.

{invesytoolbox-0.0.22/src/invesytoolbox.egg-info → invesytoolbox-0.0.23}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: invesytoolbox
-Version: 0.0.22
+Version: 0.0.23
 Summary: Tools for Python scripts or terminal
 Home-page: https://gitlab.com/Rastaf/invesytoolbox
 Author: Georg Pfolz
@@ -44,6 +44,15 @@ That's also why all date and time functions also take into account the old DateT
 The documentation can be found [here](https://rastaf.gitlab.io/invesytoolbox/).
 
 # History
+## 0.0.23 (2024-07-22)
+* **adjust_spaces_on_punctuation**: inserts narrow (or normal spaces) for certain languages
+* **value_2datatype**: 
+  - default fmt changed to None (hopefully it doesn't break somewhere, but this is necessary)
+  - 'pendulum' is now an option for the parameter 
+- default for parameter **fmt** changed to None (this is necessary for the new pendulum conversion in **value_2datatype** to work) for
+	- **dict_2datatypes**
+	- **dictlist_2datatypes**
+
 ## 0.0.22 (2023-10-14)
 * **normalize_name** and **could_be_a_name** now have the boolean parameter *lastname* that indicates that a single-word name is to be treated as a last name, not a first name.
 * **get_locale**: locale can be only the language, without the country.

{invesytoolbox-0.0.22 → invesytoolbox-0.0.23}/setup.cfg

@@ -1,6 +1,6 @@
 [metadata]
 name = invesytoolbox
-version = 0.0.22
+version = 0.0.23
 author = Georg Pfolz
 author_email = georg.pfolz@invesy.at
 description = Tools for Python scripts or terminal

{invesytoolbox-0.0.22 → invesytoolbox-0.0.23}/src/invesytoolbox/itb_data.py

@@ -8,6 +8,7 @@ from typing import Union, List, Dict, Any, Optional
 import DateTime
 import datetime
 import vobject
+import pendulum
 from dateutil.parser import parse
 from itb_date_time import convert_datetime, str_to_date, str_to_DT, get_dateformat
 from itb_email_phone import process_phonenumber
@@ -38,9 +39,7 @@ def dict_from_dict_list(
     single_value: Optional[bool] = None,
     include_key: Optional[bool] = False
 ) -> dict:
-    """Create a dictionary from a list of dictionaries
-
-    .. note:: The annotated return type is not true if a single_value argument is given.
+    """ Create a dictionary from a list of dictionaries
 
     :param dictList: the list of dictionaries to be converted
     :param key: the key of the dictionaries to use as key for the new dictionary.
@@ -70,7 +69,7 @@ def create_vcard(
     data: Dict[str, str],
     returning: str = 'vcard'
 ) -> str:
-    """create a vCard from a dictionary
+    """ create a vCard from a dictionary
 
     .. note:: The serialized vcard has Windows line-breaks, which is fine, I guess
     .. note:: colons in notes are escaped in vobject
@@ -134,7 +133,7 @@ def dict_2unicode(
     d: Dict[Union[str, bytes], Any],
     encoding: str = 'utf-8'
 ) -> dict:
-    """ Converts all keys and values in a dictionary from bytes to unicode
+    """ Convert all keys and values in a dictionary from bytes to unicode
 
     All keys and values are changed from bytes to unicode, if applicable.
     Other data types are left unchaged, including other compound data types.
@@ -156,9 +155,27 @@ def dict_2datatypes(
     convert_keys: bool = False,
     convert_to_unicode: bool = False,
     dt: str = 'datetime',
-    fmt: str = '%d.%m.%Y'
+    fmt: str = None
 ) -> Dict[Any, Any]:
-    """ convert all data of a dictionary to specific (json metadata) or guessed types """
+    """ Convert all data of a dictionary to specific (json metadata) or guessed types
+
+    :param d: dictionary
+    :param metadata: dictionary containing types for the keys:
+               - boolean
+               - int
+               - float
+               - date
+               - datetime: date and time
+               - time: conversion or not based on dt
+    :param convert_keys: convert keys to unicode
+    :param convert_to_unicode: convert all bytes to unicode in the process
+    :param dt: - datetime or dt
+               - DateTime or DT
+               - ignore or string
+               - pendulum
+               - default: datetime, because it's Python's default
+    :param fmt: format for datetime parsing
+    """
 
     if convert_keys:
         return {
@@ -197,15 +214,35 @@ def dictlist_2datatypes(
     convert_keys: bool = False,
     convert_to_unicode: bool = False,
     dt: str = 'datetime',
-    fmt: str = '%d.%m.%Y'
+    fmt: str = None
 ) -> list:
+    """ Convert all data of a list of dictionaries to specific (json metadata) or guessed types
+
+    :param dictList: list of dictionaries
+    :param metadata: dictionary containing types for the keys:
+                - boolean
+                - int
+                - float
+                - date
+                - datetime: date and time
+                - time: conversion or not based on dt
+    :param convert_keys: convert keys to unicode
+    :param convert_to_unicode: convert all bytes to unicode in the process
+    :param dt: - datetime or dt
+               - DateTime or DT
+               - ignore or string
+               - pendulum
+               - default: datetime, because it's Python's default
+    :param fmt: format for datetime parsing
+    """
     return [
         dict_2datatypes(
             d=dic,
             metadata=metadata,
             convert_keys=convert_keys,
             convert_to_unicode=convert_to_unicode,
-            dt=dt
+            dt=dt,
+            fmt=fmt
         )
         for dic
         in dictlist
@@ -258,17 +295,18 @@ def value_2datatype(
     convert_to_unicode: bool = False,
     encoding: str = 'utf-8',
     dt: str = 'datetime',
-    fmt: str = '%d.%m.%Y',  # only for datetime
-    UTC: bool = False
+    fmt: str = None,
+    timezone: str = 'local'
 ) -> Union[str, int, float]:
     """ Convert a value to a datatype
 
     this function has two modes:
 
-    1. it is provided a type for the conversion
+    1. a type is provided for the conversion
     2. it makes educated guesses in converting a string
 
     :param value:
+    :param typ: type for the conversion
     :param metadata: dictionary containing types for the keys:
                - boolean
                - int
@@ -281,7 +319,10 @@ def value_2datatype(
     :param encoding: if bytes are present, use this encoding to convert them to unicode
     :param dt: - datetime or dt
                - DateTime or DT
+               - ignore or string
+               - pendulum
                - default: datetime, because it's Python's default
+    :param timezone: default is 'local', other options are 'UTC' or 'Europe/Vienna'
     """
     if typ:
         if typ == 'boolean':
@@ -311,6 +352,17 @@ def value_2datatype(
                     value,
                     datefmt='international'
                 ) + 0.5  # to avoid day-shifting due to timezones, use 12am
+            elif dt == 'pendulum':
+                if fmt:
+                    p_dt = pendulum.from_format(value, fmt)
+                else:
+                    p_dt = pendulum.parse(value)
+
+                if p_dt.tzinfo == 'UTC' and timezone == 'local':
+                    return p_dt.in_tz(pendulum.local_timezone())
+                elif timezone:
+                    return p_dt.in_tz(timezone)
+                return p_dt.date()
             elif dt in ('ignore', 'string'):
                 return value
             else:
@@ -327,6 +379,17 @@ def value_2datatype(
                     )
                 except DateTime.interfaces.SyntaxError:
                     return value
+            elif dt == 'pendulum':
+                if fmt:
+                    p_dt = pendulum.from_format(value, fmt)
+                else:
+                    p_dt = pendulum.parse(value)
+
+                if p_dt.tzinfo == 'UTC' and timezone == 'local':
+                    return p_dt.in_tz(pendulum.local_timezone())
+                elif timezone:
+                    return p_dt.in_tz(timezone)
+                return p_dt
             elif dt in ('ignore', 'string'):
                 return value
             else:
@@ -339,7 +402,6 @@ def value_2datatype(
                 return value  # DT: return the string
 
     else:
-
         if isinstance(value, (bool, int, float)):
             return value
 
@@ -373,12 +435,7 @@ def value_2datatype(
                     datestring=value,
                     checkonly=True
                 ):
-                    if ':' in value:
-                        return convert_datetime(
-                            date=value,
-                            convert_to=dt
-                        )
-                    elif dt in ('datetime', 'dt'):
+                    if dt in ('datetime', 'dt'):
                         return str_to_date(
                             datestring=value
                         )
@@ -386,6 +443,22 @@ def value_2datatype(
                         return str_to_DT(
                             datestring=value
                         )
+                    elif dt == 'pendulum':
+                        if fmt:
+                            p_dt = pendulum.from_format(value, fmt)
+                        else:
+                            p_dt = pendulum.parse(value)
+                
+                        if p_dt.tzinfo == 'UTC' and timezone == 'local':
+                            return p_dt.in_tz(pendulum.local_timezone())
+                        elif timezone:
+                            return p_dt.in_tz(timezone)
+                        return p_dt
+                    else:
+                        return convert_datetime(
+                            date=value,
+                            convert_to=dt
+                        )
 
             except Exception:
                 # in case it's a subset of datetime_chars but not a date or datetime or time

{invesytoolbox-0.0.22 → invesytoolbox-0.0.23}/src/invesytoolbox/itb_date_time.py

@@ -37,6 +37,8 @@ def is_valid_datetime_string(
     a conflict with 4-digit year values, it is considered invalid
 
     :param returning: can return a tuple
+
+    .. note:: This does not work with ISO8601 strings! (returns False)
     """
     return str_to_dt(
         datestring=datestring,
@@ -57,6 +59,14 @@ def get_dateformat(
     :todo: times!
     :raises ValueError: if an invalid datetime or DateTime string is provided
     """
+    # first let's check for ISO8601 strings
+    if checkonly:
+        try:
+            pendulum.parse(datestring)
+            return True
+        except pendulum.parsing.exceptions.ParserError:
+            pass  # don't return False, because it may be a valid date string
+
     timefmt = ''
     if ' ' in datestring:
         try:
@@ -225,7 +235,7 @@ def str_to_pendulum(
     if not fmt:
         return pendulum.parse(datestring)
     else:
-        return pendulum.datetime.strptime(datestring, fmt)
+        return pendulum.from_format(datestring, fmt)
 
 
 def str_to_date(

{invesytoolbox-0.0.22 → invesytoolbox-0.0.23}/src/invesytoolbox/itb_html.py

@@ -15,7 +15,7 @@ def prettify_html(
 
     .. note:: This function is needed for Zope Python Scripts
         because even if bs4 can be imported, prettify throws
-        an Unauthorized error in restricted Python
+        an Unauthorized error in Restricted Python
     """
 
     return BeautifulSoup(html, "html.parser").prettify()

{invesytoolbox-0.0.22 → invesytoolbox-0.0.23}/src/invesytoolbox/itb_text_name.py

@@ -14,7 +14,7 @@ from nameparser import HumanName
 d = gender.Detector(case_sensitive=False)
 
 
-char_nb_map = {
+CHAR_NB_MAP = {
     'a': ('a', '4', '@'),
     'b': ('b', '6', '8', 'I3', '13', '!3'),
     'c': ('c', '('),
@@ -43,6 +43,54 @@ char_nb_map = {
     'z': ('z', '2', '7_')
 }
 
+# regex pattern
+LANG_PUNCT_SPACES = {
+    'fr': {
+        'regex': r'([!?:;%])',
+        'narrow': '\u202f\\1',
+        'normal': r' \1'
+    },
+    'es': {
+        'regex': r'([¿¡])',
+        'narrow': '\\1\u202f',
+        'normal': r'\1 '
+    },
+    'ro': {
+        'regex': r'([!?:;])',
+        'narrow': '\u202f\\1',
+        'normal': r' \1'
+    }
+}
+
+def adjust_spaces_on_punctuation(
+    text: str,
+    language: str,
+    space: str = 'narrow'
+):
+    """
+    Adjust spaces before or after punctuation marks according to the language.
+    By default the narrow space (\u202f) is used for adjustments.
+    """
+    # Step 1: Remove existing spaces before the punctuation
+    text = re.sub(r'\s+([!?:;%\),.])', r'\1', text)
+
+    lang_data = LANG_PUNCT_SPACES.get(language)
+
+    if lang_data:
+        # Step 2: Add a narrow space (\u202f) before the punctuation
+        try:
+            text = re.sub(
+                lang_data['regex'],
+                lang_data[space],
+                text
+            )
+        except re.error as e:
+            raise Exception(f"Error in regex for language {language}: {e}")
+    else:
+        # Original behavior for other languages
+        text = re.sub(r'\s+([,.!?;:\)])', r'\1', text)
+    return text
+
 
 def and_list(
     elements: list,
@@ -202,7 +250,7 @@ def leet(
         if not c.isalnum():
             continue  # without counting
 
-        c = random.choice(char_nb_map[c])
+        c = random.choice(CHAR_NB_MAP[c])
 
         if not random.randrange(change_uppercase):
             c = c.upper()

{invesytoolbox-0.0.22 → invesytoolbox-0.0.23/src/invesytoolbox.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: invesytoolbox
-Version: 0.0.22
+Version: 0.0.23
 Summary: Tools for Python scripts or terminal
 Home-page: https://gitlab.com/Rastaf/invesytoolbox
 Author: Georg Pfolz
@@ -44,6 +44,15 @@ That's also why all date and time functions also take into account the old DateT
 The documentation can be found [here](https://rastaf.gitlab.io/invesytoolbox/).
 
 # History
+## 0.0.23 (2024-07-22)
+* **adjust_spaces_on_punctuation**: inserts narrow (or normal spaces) for certain languages
+* **value_2datatype**: 
+  - default fmt changed to None (hopefully it doesn't break somewhere, but this is necessary)
+  - 'pendulum' is now an option for the parameter 
+- default for parameter **fmt** changed to None (this is necessary for the new pendulum conversion in **value_2datatype** to work) for
+	- **dict_2datatypes**
+	- **dictlist_2datatypes**
+
 ## 0.0.22 (2023-10-14)
 * **normalize_name** and **could_be_a_name** now have the boolean parameter *lastname* that indicates that a single-word name is to be treated as a last name, not a first name.
 * **get_locale**: locale can be only the language, without the country.

{invesytoolbox-0.0.22 → invesytoolbox-0.0.23}/src/tests/test_data.py

@@ -8,18 +8,21 @@ import sys
 import unittest
 import datetime
 import DateTime
+import pendulum
 from dateutil.parser import parse
 
 sys.path.append(".")
 
-from itb_data import \
-    any_2boolean, \
-    create_vcard, \
-    dict_2unicode, \
-    dict_2datatypes, \
-    dict_from_dict_list, \
-    dictlist_2datatypes, \
-    sort_dictlist
+from itb_data import (
+    any_2boolean,
+    create_vcard,
+    dict_2unicode,
+    dict_2datatypes,
+    dict_from_dict_list,
+    dictlist_2datatypes,
+    sort_dictlist,
+    value_2datatype
+)
 
 dict_list = [
     {'a': 1, 'b': 2, 'c': 5},
@@ -154,6 +157,9 @@ END:VCARD
 
 
 class TestData(unittest.TestCase):
+    # verbose, show complete diff
+    maxDiff = None
+
     def test_any_2boolean(self):
         for a, b in test_boolean.items():
             self.assertEqual(
@@ -260,7 +266,28 @@ class TestData(unittest.TestCase):
         )
 
     def test_value_2datatype(self):
-        pass  # this is already tested extensively in test_dict_2datatypes
+        # this is already tested extensively in test_dict_2datatypes
+        # so we just test pendulum here
+        print('test_value_2datatype: this should result in pendulum datetimes')
+        value = '01.04.2022 10:32'
+        fmt = 'DD.MM.YYYY HH:mm'
+
+        p = value_2datatype(
+            value=value,
+            typ='datetime',
+            dt='pendulum',
+            fmt=fmt
+        )
+        print(value, '→', p, p.tzinfo)
+
+        value = '2024-04-01T10:32:00'
+
+        p = value_2datatype(
+            value=value,
+            dt='pendulum'
+        )
+        print(value, '→', p, p.tzinfo)
+
 
     def test_sort_dictlist(self):
         sorted_dict_list = sort_dictlist(
@@ -297,6 +324,10 @@ class TestData(unittest.TestCase):
         )
 
     def test_dictlist_2datatypes(self):
+        # print('dict_for_testing', dict_for_testing)
+        # print('dict_for_testing_datatyped_unicoded', dict_for_testing_datatyped_unicoded)
+
+
         dictlist_for_testing = [
             dict_for_testing,
             dict_for_testing,
@@ -323,6 +354,16 @@ class TestData(unittest.TestCase):
             dictlist_tested_datatyped
         )
 
+        dictlist_pendulum = dictlist_2datatypes(
+            dictlist=dictlist_for_testing,
+            convert_keys=True,
+            convert_to_unicode=True,
+            dt='pendulum',
+            fmt='DD.MM.YYYY'
+        )
+
+        print('dictlist_pendulum', dictlist_pendulum)
+
 
 if __name__ == '__main__':
     unittest.main()

{invesytoolbox-0.0.22 → invesytoolbox-0.0.23}/src/tests/test_text_name.py

@@ -11,6 +11,7 @@ import random
 sys.path.append(".")
 
 from itb_text_name import (
+    adjust_spaces_on_punctuation,
     and_list,
     capitalize_name,
     get_gender,
@@ -295,8 +296,40 @@ reference_names_sorted = [
 
 lower_text = 'das ist ein Beispiel-Text, der kapitalisiert werden kann.'
 
+# Language Texts (for adjusting spaces on the indentation)
+punct_texts = {
+    'de': "Hallo Welt ! Wie geht es Ihnen ? Ich hoffe, Sie haben einen schönen Tag : Das Wetter ist herrlich . Wussten Sie, dass 75 % aller Statistiken erfunden sind?",
+    'en': "Hello world ! How are you today ? I hope you're having a great day : The weather is lovely . Did you know that 80 % of all statistics are made up?",
+    'fr': "Bonjour le monde! Comment allez-vous aujourd'hui? J'espère que vous passez une bonne journée: Le temps est magnifique . Saviez-vous que 85% des statistiques sont inventées?",
+    'es': "¡Hola mundo! ¿Cómo estás hoy ? Espero que tengas un buen día : El clima es hermoso. ¿Sabías que el 90 % de las estadísticas son inventadas ?",
+    'ro': "Salut lume! Cum ești azi? Sper că ai o zi bună: Vremea este minunată.Știai că 95 % din statistici sunt inventate?"
+}
+
+punct_texts_corrected = {
+    'de': "Hallo Welt! Wie geht es Ihnen? Ich hoffe, Sie haben einen schönen Tag: Das Wetter ist herrlich. Wussten Sie, dass 75% aller Statistiken erfunden sind?",
+    'en': "Hello world! How are you today? I hope you're having a great day: The weather is lovely. Did you know that 80% of all statistics are made up?",
+    'fr': "Bonjour le monde\u202f! Comment allez-vous aujourd'hui\u202f? J'espère que vous passez une bonne journée\u202f: Le temps est magnifique. Saviez-vous que 85\u202f% des statistiques sont inventées\u202f?",
+    'es': "¡\u202fHola mundo! ¿\u202fCómo estás hoy? Espero que tengas un buen día: El clima es hermoso. ¿\u202fSabías que el 90% de las estadísticas son inventadas?",
+    'ro': "Salut lume\u202f! Cum ești azi\u202f? Sper că ai o zi bună\u202f: Vremea este minunată.Știai că 95% din statistici sunt inventate\u202f?"
+}
 
 class TestTextName(unittest.TestCase):
+    def test_adjust_spaces_on_punctuation(self):
+        for lang, text in punct_texts.items():
+            print(f'Language: {lang}')
+            try:
+                corrected_text = adjust_spaces_on_punctuation(
+                    text = text,
+                    language = lang
+                )
+            except Exception as e:
+                print(f'Error: {e}')
+                raise AssertionError(f'Error: {e}')
+            self.assertEqual(
+                corrected_text,
+                punct_texts_corrected[lang]
+            )
+    
     def test_and_list(self):
         a_list = [1, 'Georg', 'Haus', True]
         correct_str = '1, Georg, Haus and True'