Skip to content

Latest commit

 

History

History
54 lines (43 loc) · 3.22 KB

CHANGELOG.md

File metadata and controls

54 lines (43 loc) · 3.22 KB
Raw

Changelog

0.8.0 (unreleased yet)

  • Added support for ISO-639 language codes (en, de, sk, ...). #106
  • TextRankSummarizer uses iterative algorithm. Previous algorithm is called ReductionSummarizer. #100

0.7.0 (2017-07-22)

  • Added support for Chinese. #93

0.6.0 (2017-03-05)

  • Dropped support for distutils when installing sumy.
  • Added support for Japanese. #79
  • Fixed incorrect n-grams computation for more sentences. #84
  • Fixed NLTK dependency for Python 3.3. NLTK 3.2 dropped support for Python 3.3 so sumy needs 3.1.

0.5.1 (2016-11-17)

  • Fixed missing stopwords in SumBasic summarizer. #74

0.5.0 (2016-11-12)

  • Added "--text" CLI parameter to summarize text in Emacs and other tools. #67
  • Fixed computation of cosine similarity in LexRank summarizator. #63
  • Fixed resource searching in .egg packages. #53

0.4.1 (2016-03-06)

  • Added support for Portuguese and Spanish. #49 #51
  • Better error message when NLTK tokenizers are missing.

0.4.0 (2015-12-04)

  • Dropped support for Python 2.6 and 3.2. Only 2.7/3.3+ are officially supported now. Time to move :)
  • CLI: Better message for unknown format.
  • LexRank: fixed power method computation.
  • Added some extra abbreviations (english, german) into tokenizer for better output.
  • SumBasic: Added new summarization method - SumBasic. Thanks to Julian Griggs.
  • KL: Added new summarization method - KL. Thanks to Julian Griggs.
  • Added dependency requests to fix issues with downloading pages.
  • Better documentation of expected Plaintext document format.

0.3.0 (2014-06-07)

  • Added possibility to specify format of input document for URL & stdin. Thanks to @Lucas-C.
  • Added possibility to specify custom file with stop-words in CLI. Thanks to @Lucas-C.
  • Added support for French language (added stopwords & stemmer). Thanks to @Lucas-C.
  • Function sumy.utils.get_stop_words raises LookupError instead of ValueError for unknown language.
  • Exception LookupError is raised for unknown language of stemmer instead of falling silently to null_stemmer.

0.2.1 (2014-01-23)

  • Fixed installation of my own readability fork. Added breadability to the dependencies instead of it #8. Thanks to @pratikpoddar.

0.2.0 (2014-01-18)

  • Removed dependency on SciPy #7. Use numpy.linalg.svd implementation. Thanks to Shantanu.

0.1.0 (2013-10-20)

  • First public release.