Merge pull request #83 from allo-media/master

Version 2.5.0
allo-media · Dec 9, 2022 · a24659d · a24659d
2 parents 47dda52 + 636301c
commit a24659d
Show file tree

Hide file tree

Showing 26 changed files with 2,527 additions and 242 deletions.
diff --git a/.circleci/config.yml b/.circleci/config.yml
@@ -47,10 +47,10 @@ jobs:
           name: build doc
           command: |
             . venv/bin/activate
-            cd doc && make html
+            cd docs && make html
 
       - store_artifacts:
-          path: doc/_build/html/
+          path: docs/_build/html/
           destination: html-doc
 
   deploy:

diff --git a/README.rst b/README.rst
@@ -6,8 +6,9 @@ text2num
 
 ``text2num`` is a python package that provides functions and parser classes for:
 
-- parsing numbers expressed as words in French, English, Spanish and Portuguese and convert them to integer values;
-- detect ordinal, cardinal and decimal numbers in a stream of French, English, Spanish and Portuguese words and get their decimal digit representations. Spanish does not support ordinal numbers yet.
+- Parsing of numbers expressed as words in French, English, Spanish, Portuguese, German and Catalan and convert them to integer values.
+- Detection of ordinal, cardinal and decimal numbers in a stream of French, English, Spanish and Portuguese words and get their decimal digit representations. NOTE: Spanish does not support ordinal numbers yet.
+- Detection of ordinal, cardinal and decimal numbers in a German text (BETA). NOTE: No support for 'relaxed=False' yet (behaves like 'True' by default).
 
 Compatibility
 -------------
@@ -73,6 +74,26 @@ English examples:
     >>> text2num("eighty-one", "en")
     81
 
+
+Russian examples:
+
+.. code-block:: python
+
+    >>> from text_to_num import text2num
+
+    >>> text2num("пятьдесят один миллион пятьсот семьдесят восемь тысяч триста два", "ru")
+    51578302
+
+    >>> text2num("миллиард миллион тысяча один", "ru")
+    1001001001
+
+    >>> text2num("один миллиард один миллион одна тысяча один", "ru")
+    1001001001
+
+    >>> text2num("восемьдесят один", "ru")
+    81
+
+
 Spanish examples:
 
 .. code-block:: python
@@ -102,6 +123,41 @@ Portuguese examples:
     >>> text2num("vinte e quatro milhões duzentos mil quarenta e sete", "pt")
     24200047
 
+
+German examples:
+
+.. code-block:: python
+
+    >>> from text_to_num import text2num
+
+    >>> text2num("einundfünfzigmillionenfünfhundertachtundsiebzigtausenddreihundertzwei", "de")
+    51578302
+
+    >>> text2num("ein und achtzig", "de")
+    81
+
+
+Catalan examples:
+
+.. code-block:: python
+
+    >>> from text_to_num import text2num
+    >>> text2num('noranta-cinc', "ca")
+    95
+
+    >>> text2num('huitanta-u', "ca")
+    81
+
+    >>> text2num('mil nou-cents noranta-nou', "ca")
+    1999
+
+    >>> text2num("cinquanta-un milions cinc-cents setanta-vuit mil tres-cents dos", "ca")
+    51578302
+
+    >>> text2num('mil mil dos-cents', "ca")
+    ValueError: invalid literal for text2num: 'mil mil dos-cents'
+
+
 Find and transcribe
 ~~~~~~~~~~~~~~~~~~~
 
@@ -113,23 +169,27 @@ French:
 
     >>> from text_to_num import alpha2digit
     >>> sentence = (
-    ...         "Huit cent quarante-deux pommes, vingt-cinq chiens, mille trois chevaux, "
-    ...         "douze mille six cent quatre-vingt-dix-huit clous.\n"
-    ...         "Quatre-vingt-quinze vaut nonante-cinq. On tolère l'absence de tirets avant les unités : "
-    ...         "soixante seize vaut septante six.\n"
-    ...         "Nombres en série : douze quinze zéro zéro quatre vingt cinquante-deux cent trois cinquante deux "
-    ...         "trente et un.\n"
-    ...         "Ordinaux: cinquième troisième vingt et unième centième mille deux cent trentième.\n"
-    ...         "Décimaux: douze virgule quatre-vingt dix-neuf, cent vingt virgule zéro cinq ; "
-    ...         "mais soixante zéro deux."
-    ...     )
-    >>> print(alpha2digit(sentence))
+    ...     "Huit cent quarante-deux pommes, vingt-cinq chiens, mille trois chevaux, "
+    ...     "douze mille six cent quatre-vingt-dix-huit clous.\n"
+    ...     "Quatre-vingt-quinze vaut nonante-cinq. On tolère l'absence de tirets avant les unités : "
+    ...     "soixante seize vaut septante six.\n"
+    ...     "Nombres en série : douze quinze zéro zéro quatre vingt cinquante-deux cent trois cinquante deux "
+    ...     "trente et un.\n"
+    ...     "Ordinaux: cinquième troisième vingt et unième centième mille deux cent trentième.\n"
+    ...     "Décimaux: douze virgule quatre-vingt dix-neuf, cent vingt virgule zéro cinq ; "
+    ...     "mais soixante zéro deux."
+    ... )
+    >>> print(alpha2digit(sentence, "fr", ordinal_threshold=0))
     842 pommes, 25 chiens, 1003 chevaux, 12698 clous.
     95 vaut 95. On tolère l'absence de tirets avant les unités : 76 vaut 76.
     Nombres en série : 12 15 004 20 52 103 52 31.
     Ordinaux: 5ème 3ème 21ème 100ème 1230ème.
     Décimaux: 12,99, 120,05 ; mais 60 02.
 
+    >>> sentence = "Cinquième premier second troisième vingt et unième centième mille deux cent trentième."
+    >>> print(alpha2digit(sentence, "fr", ordinal_threshold=3))
+    5ème premier second troisième 21ème 100ème 1230ème.
+
 
 English:
 
@@ -142,7 +202,23 @@ English:
     'On May 23rd, I bought 25 cows, 12 chickens and 125.40 kg of potatoes.'
 
 
-Spanish (ordinals not supported):
+Russian:
+
+.. code-block:: python
+
+    >>> from text_to_num import alpha2digit
+
+    >>> # дробная часть не обрабатывает уточнения вроде "пять десятых", "двенадцать сотых", "сколько-то стотысячных" и т.п., поэтому их лучше опускать
+    >>> text = "Двадцать пять коров, двенадцать сотен цыплят и сто двадцать пять точка сорок кг картофеля."
+    >>> alpha2digit(text, "ru")
+    '25 коров, 1200 цыплят и 125.40 кг картофеля.'
+
+    >>> text = "каждый пятый на первый второй расчитайсь!"
+    >>> alpha2digit(text, 'ru', ordinal_threshold=0)
+    'каждый 5ый на 1ый 2ой расчитайсь!'
+
+
+Spanish (ordinals not supported yet):
 
 .. code-block:: python
 
@@ -169,12 +245,68 @@ Portuguese:
 
     >>> text = "Temos mais vinte graus dentro e menos quinze fora."
     >>> alpha2digit(text, "pt")
-   'Temos +20 graus dentro e -15 fora.'
+    'Temos +20 graus dentro e -15 fora.'
 
     >>> text = "Ordinais: quinto, terceiro, vigésimo, vigésimo primeiro, centésimo quarto"
-   >>> alpha2digit(text, "pt")
-   'Ordinais: 5º, terceiro, 20ª, 21º, 104º'
+    >>> alpha2digit(text, "pt")
+    'Ordinais: 5º, terceiro, 20ª, 21º, 104º'
+
 
+German (BETA, Note: 'relaxed' parameter is not supported yet and 'True' by default):
+
+.. code-block:: python
+
+    >>> from text_to_num import alpha2digit
+
+    >>> text = "Ich habe fünfundzwanzig Kühe, zwölf Hühner und einhundertfünfundzwanzig kg Kartoffeln gekauft."
+    >>> alpha2digit(text, "de")
+    'Ich habe 25 Kühe, 12 Hühner und 125 kg Kartoffeln gekauft.'
+
+    >>> text = "Die Temperatur beträgt minus fünfzehn Grad."
+    >>> alpha2digit(text, "de")
+    'Die Temperatur beträgt -15 Grad.'
+
+    >>> text = "Die Telefonnummer lautet plus dreiunddreißig neun sechzig null sechs zwölf einundzwanzig."
+    >>> alpha2digit(text, "de")
+    'Die Telefonnummer lautet +33 9 60 0 6 12 21.'
+
+    >>> text = "Der zweiundzwanzigste Januar zweitausendzweiundzwanzig."
+    >>> alpha2digit(text, "de")
+    '22. Januar 2022'
+
+    >>> text = "Es ist ein Buch mit dreitausend Seiten aber nicht das erste."
+    >>> alpha2digit(text, "de", ordinal_threshold=0)
+    'Es ist ein Buch mit 3000 Seiten aber nicht das 1..'
+
+    >>> text = "Pi ist drei Komma eins vier und so weiter, aber nicht drei Komma vierzehn :-p"
+    >>> alpha2digit(text, "de", ordinal_threshold=0)
+    'Pi ist 3,14 und so weiter, aber nicht 3 Komma 14 :-p'
+
+
+Catalan:
+
+.. code-block:: python
+
+    >>> from text_to_num import alpha2digit
+    >>> text = ("Huit-centes quaranta-dos pomes, vint-i-cinc gossos, mil tres cavalls, dotze mil sis-cents noranta-huit claus.\n Vuitanta-u és igual a huitanta-u.\n Nombres en sèrie: dotze quinze zero zero quatre vint cinquanta-dos cent tres cinquanta-dos trenta-u.\n Ordinals: cinquè tercera vint-i-uena centè mil dos-cents trentena.\n Decimals: dotze coma noranta-nou, cent vint coma zero cinc; però seixanta zero dos.")
+    >>> print(alpha2digit(text, "ca", ordinal_threshold=0))
+    842 pomes, 25 gossos, 1003 cavalls, 12698 claus.
+    81 és igual a 81.
+    Nombres en sèrie: 12 15 004 20 52 103 52 31.
+    Ordinals: 5è 3a 21a 100è 1230a.
+    Decimals: 12,99, 120,05; però 60 02.
+
+    >>> text = "Cinqué primera segona tercer vint-i-ué centena mil dos-cents trenté."
+    >>> print(alpha2digit(text, "ca", ordinal_threshold=3))
+    5é primera segona tercer 21é 100a 1230é.
+
+    >>> text = "Compràrem vint-i-cinc vaques, dotze gallines i cent vint-i-cinc coma quaranta kg de creïlles."
+    >>> alpha2digit(text, "ca")
+    'Compràrem 25 vaques, 12 gallines i 125,40 kg de creïlles.'
+
+    >>> text = "Fa més vint graus dins i menys quinze fora."
+    >>> alpha2digit(text, "ca")
+    'Fa +20 graus dins i -15 fora.'
 
 
 Read the complete documentation on `ReadTheDocs <http://text2num.readthedocs.io/>`_.

diff --git a/doc/Makefile → docs/Makefile b/doc/Makefile → docs/Makefile
diff --git a/doc/api.rst → docs/api.rst b/doc/api.rst → docs/api.rst
diff --git a/doc/conf.py → docs/conf.py b/doc/conf.py → docs/conf.py
@@ -61,7 +61,7 @@
 #
 # This is also used if you do content translation via gettext catalogs.
 # Usually you set "language" from the command line for these cases.
-language = None
+language = "en"
 
 # List of patterns, relative to source directory, that match files and
 # directories to ignore when looking for source files.

diff --git a/doc/contribute.rst → docs/contributing.rst b/doc/contribute.rst → docs/contributing.rst
@@ -29,14 +29,14 @@ Install from sources
 First, create and activate a virtual environment with the tool of you preference.
 
 Then clone https://github.com/allo-media/text2num in your workspace.
-If you are going to submit some patches, you should fork the project on Github and clone
+If you are going to submit some patches, you should fork the project on GitHub and clone
 your own fork in your workspace.
 
 Finally, install the sources in-place::
 
     python setup.py develop
 
-You do that once. Then, any change you make to the code is immediatly visible when you import the modules.
+You do that once. Then, any change you make to the code is immediately visible when you import the modules.
 
 Run the tests
 -------------
@@ -55,6 +55,16 @@ We also use mypy::
 Submit changes
 --------------
 
-If you wish to submit changes, fork the projec on github, and clone your own fork locally.
+If you wish to contribute code or documentation to the project, you should first open an issue
+on https://github.com/allo-media/text2num/issues to describe what you intend to do, and
+why:
+
+* if it's a bug fix, link to the related issues or describe precisely, with examples, what the faulty behavior is;
+* if it's a new feature, describe the use case, with examples, and why it matters;
+* if it's new or updated documentation, describe precisely which parts you are going to edit, to avoid edition conflicts;
+* if it's support for a new language, announce it clearly in order to avoid duplicate effort and to get help from other people interested in that language.
+
+Once you get positive feedback on your issue, you can fork the project on GitHub and start working on the code.
 
 All PR should be made from a dedicated branch, not from *master*, please.
+Please check your files are in proper Unicode encoded as UTF-8, and that the line endings follow the Unix convention (LF).
diff --git a/doc/index.rst → docs/index.rst b/doc/index.rst → docs/index.rst
@@ -19,7 +19,7 @@ Welcome to text2num's documentation!
    :caption: Contents:
 
    quickstart
-   contribute
+   contributing
    api
    license
 

diff --git a/doc/license.rst → docs/license.rst b/doc/license.rst → docs/license.rst
diff --git a/doc/quickstart.rst → docs/quickstart.rst b/doc/quickstart.rst → docs/quickstart.rst
diff --git a/setup.py b/setup.py
@@ -1,7 +1,7 @@
 from setuptools import setup, find_packages
 
 
-VERSION = "2.4.0"
+VERSION = "2.5.0"
 
 
 def readme():
@@ -12,7 +12,7 @@ def readme():
 setup(
     name="text2num",
     version=VERSION,
-    description="Parse and convert numbers written in French, Spanish, English or Portuguese into their digit representation.",
+    description="Parse and convert numbers written in French, Spanish, English, Portuguese, German, Catalan or Russion into their digit representation.",
     long_description=readme(),
     classifiers=[
         "Development Status :: 5 - Production/Stable",
@@ -23,9 +23,12 @@ def readme():
         "Natural Language :: French",
         "Natural Language :: English",
         "Natural Language :: Spanish",
-        "Natural Language :: Portuguese"
+        "Natural Language :: Portuguese",
+        "Natural Language :: German",
+        "Natural Language :: Catalan",
+        "Natural Language :: Russian"
     ],
-    keywords="French, Spanish, English and Portuguese NLP words-to-numbers",
+    keywords="French Spanish English Portuguese German Catalan Russion NLP words-to-numbers",
     url="https://github.com/allo-media/text2num",
     author="Allo-Media",
     author_email="[email protected]",