Skip to main content

Bindings to UDPipe library

Project description

ufal.udpipe

The ufal.udpipe is a Python binding to UDPipe library <http://ufal.mff.cuni.cz/udpipe>.

The bindings is a straightforward conversion of the C++ bindings API. In Python 2, strings can be both unicode and UTF-8 encoded str, and the library always produces unicode. In Python 3, strings must be only str.

Wrapped C++ API

The C++ API being wrapped follows. For a API reference of the original C++ API, see <http://ufal.mff.cuni.cz/udpipe/api-reference>.

Helper Structures
-----------------

  typedef vector<int> Children;

  typedef vector<string> Comments;

  class ProcessingError {
  public:
    bool occurred();
    string message;
  };

  class Word {
   public:
    int id;         // 0 is root, >0 is sentence word, <0 is undefined
    string form;    // form
    string lemma;   // lemma
    string upostag; // universal part-of-speech tag
    string xpostag; // language-specific part-of-speech tag
    string feats;   // list of morphological features
    int head;       // head, 0 is root, <0 is undefined
    string deprel;  // dependency relation to the head
    string deps;    // secondary dependencies
    string misc;    // miscellaneous information

    Children children;

    Word(int id = -1, const string& form = string());
  };
  typedef vector<Word> Words;

  class MultiwordToken {
   public:
    int idFirst, idLast;
    string form;
    string misc;

    MultiwordToken(int id_first = -1, int id_last = -1, const string& form = string(), const string& misc = string());
  };
  typedef vector<MultiwordToken> MultiwordTokens;

  class Sentence {
   public:
    Sentence();

    Words words;
    MultiwordTokens multiwordTokens;
    Comments comments
    static const string rootForm;

    bool empty();
    void clear();
    virtual Word& addWord(const char* form);
    void setHead(int id, int head, const string& deprel);
    void unlinkAllWords();
  };
  typedef vector<Sentence> Sentences;


Main Classes
------------

  class InputFormat {
   public:
    virtual void setText(const char* text);
    virtual bool nextSentence(Sentence& s, ProcessingError* error = nullptr);

    static InputFormat* newInputFormat(const string& name);
    static InputFormat* newConlluInputFormat();
    static InputFormat* newHorizontalInputFormat();
    static InputFormat* newVerticalInputFormat();
  };

  class OutputFormat {
   public:
    virtual string writeSentence(const Sentence& s) const;

    static OutputFormat* newOutputFormat(const string& name);
    static OutputFormat* newConlluOutputFormat();
    static OutputFormat* newHorizontalOutputFormat();
    static OutputFormat* newVerticalOutputFormat();
  };

  class Model {
   public:
    static Model* load(const char* fname);

    virtual InputFormat* newTokenizer(const string& options) const;
    virtual bool tag(Sentence& s, const string& options, ProcessingError* error = nullptr) const;
    virtual bool parse(Sentence& s, const string& options, ProcessingError* error) const;

    static const string DEFAULT;
  };

  class Pipeline {
   public:
    Pipeline(const Model* m, const string& input, const string& tagger, const string& parser, const string& output);

    void setModel(const Model* m);
    void setInput(const string& input);
    void setTagger(const string& tagger);
    void setParser(const string& parser);
    void setOutput(const string& output);

    string process(const string& data, ProcessingError* error = nullptr) const;

    static const string DEFAULT;
    static const string NONE;
  };

  class Trainer {
   public:

    static string train(const string& method, const Sentences& train, const Sentences& heldout,
                        const string& tokenizer, const string& tagger, const string& parser,
                        ProcessingError* error = nullptr);

    static const string DEFAULT;
    static const string NONE;
  };

  class Evaluator {
   public:
    Evaluator(const Model* m, const string& tokenizer, const string& tagger, const string& parser);

    void setModel(const Model* m);
    void setTokenizer(const string& tokenizer);
    void setTagger(const string& tagger);
    void setParser(const string& parser);

    string evaluate(const string& data, ProcessingError* error = nullptr) const;

    static const string DEFAULT;
    static const string NONE;
  };

  class Version {
   public:
    unsigned major;
    unsigned minor;
    unsigned patch;
    string prerelease;

    // Returns current version.
    static version current();
  };

Examples

run_udpipe

Simple pipeline loading data (tokenizing on request), tagging, parsing and writing to specified output format:

from ufal.udpipe import *

# In Python2, wrap sys.stdin and sys.stdout to work with unicode.
if sys.version_info[0] < 3:
    import codecs
    import locale
    encoding = locale.getpreferredencoding()
    sys.stdin = codecs.getreader(encoding)(sys.stdin)
    sys.stdout = codecs.getwriter(encoding)(sys.stdout)

if len(sys.argv) < 4:
    sys.stderr.write('Usage: %s input_format output_format model_file\n' % sys.argv[0])
    sys.exit(1)

sys.stderr.write('Loading model: ')
model = Model.load(sys.argv[3])
if not model:
    sys.stderr.write("Cannot load model from file '%s'\n" % sys.argv[3])
    sys.exit(1)
sys.stderr.write('done\n')

pipeline = Pipeline(model, sys.argv[1], Pipeline.DEFAULT, Pipeline.DEFAULT, sys.argv[2])
error = ProcessingError()

not_eof = True
while not_eof:
    text = ''

    # Read block
    while True:
        line = sys.stdin.readline()
        not_eof = bool(line)
        if not not_eof: break
        line = line.rstrip('\r\n')
        text += line
        text += '\n';
        if not line: break

    # Process data
    print "Processing %s" % text
    processed = pipeline.process(text, error)
    if error.occurred():
        sys.stderr.write("An error occurred when running run_udpipe: ")
        sys.stderr.write(error.message)
        sys.stderr.write("\n")
        sys.exit(1)
    sys.stdout.write(processed)

AUTHORS

Milan Straka <straka@ufal.mff.cuni.cz>

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

ufal.udpipe-1.0.0.1.tar.gz (271.1 kB view hashes)

Uploaded source

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page