From 6e2930a4a21cf6686d1c4fc59a23fda083e6ef93 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ole=20Henrik=20Skogstr=C3=B8m?= <oleskogstrom@gmail.com>
Date: Wed, 18 Jul 2018 18:55:42 +0200
Subject: [PATCH] Conll(u)-bio converter (#2525)

* Started simple conllxbiluo converter

* Fix missing BIO to BILUO conversion
---
 spacy/cli/convert.py                   |  3 +-
 spacy/cli/converters/__init__.py       |  1 +
 spacy/cli/converters/conllubio2json.py | 95 ++++++++++++++++++++++++++
 3 files changed, 98 insertions(+), 1 deletion(-)
 create mode 100644 spacy/cli/converters/conllubio2json.py

diff --git a/spacy/cli/convert.py b/spacy/cli/convert.py
index cafe027ed..1b6217a63 100644
--- a/spacy/cli/convert.py
+++ b/spacy/cli/convert.py
@@ -4,7 +4,7 @@ from __future__ import unicode_literals
 import plac
 from pathlib import Path
 
-from .converters import conllu2json, iob2json, conll_ner2json
+from .converters import conllu2json, conllubio2json, iob2json, conll_ner2json
 from ._messages import Messages
 from ..util import prints
 
@@ -12,6 +12,7 @@ from ..util import prints
 # entry to this dict with the file extension mapped to the converter function
 # imported from /converters.
 CONVERTERS = {
+    'conllubio': conllubio2json,
     'conllu': conllu2json,
     'conll': conllu2json,
     'ner': conll_ner2json,
diff --git a/spacy/cli/converters/__init__.py b/spacy/cli/converters/__init__.py
index 02b596d4d..c7d5ac198 100644
--- a/spacy/cli/converters/__init__.py
+++ b/spacy/cli/converters/__init__.py
@@ -1,3 +1,4 @@
 from .conllu2json import conllu2json
+from .conllubio2json import conllubio2json
 from .iob2json import iob2json
 from .conll_ner2json import conll_ner2json
diff --git a/spacy/cli/converters/conllubio2json.py b/spacy/cli/converters/conllubio2json.py
new file mode 100644
index 000000000..c671e2fed
--- /dev/null
+++ b/spacy/cli/converters/conllubio2json.py
@@ -0,0 +1,95 @@
+# coding: utf8
+from __future__ import unicode_literals
+
+from ...compat import json_dumps, path2str
+from ...util import prints
+from ...gold import iob_to_biluo
+
+def conllubio2json(input_path, output_path, n_sents=10, use_morphology=False):
+    """
+    Convert conllu files into JSON format for use with train cli.
+    use_morphology parameter enables appending morphology to tags, which is
+    useful for languages such as Spanish, where UD tags are not so rich.
+    """
+    # by @dvsrepo, via #11 explosion/spacy-dev-resources
+
+    docs = []
+    sentences = []
+    conll_tuples = read_conllx(input_path, use_morphology=use_morphology)
+
+    for i, (raw_text, tokens) in enumerate(conll_tuples):
+        sentence, brackets = tokens[0]
+        sentences.append(generate_sentence(sentence))
+        # Real-sized documents could be extracted using the comments on the
+        # conluu document
+        if(len(sentences) % n_sents == 0):
+            doc = create_doc(sentences, i)
+            docs.append(doc)
+            sentences = []
+
+    output_filename = input_path.parts[-1].replace(".conll", ".json")
+    output_filename = input_path.parts[-1].replace(".conllu", ".json")
+    output_file = output_path / output_filename
+    with output_file.open('w', encoding='utf-8') as f:
+        f.write(json_dumps(docs))
+    prints("Created %d documents" % len(docs),
+           title="Generated output file %s" % path2str(output_file))
+
+
+def read_conllx(input_path, use_morphology=False, n=0):
+    text = input_path.open('r', encoding='utf-8').read()
+    i = 0
+    for sent in text.strip().split('\n\n'):
+        lines = sent.strip().split('\n')
+        if lines:
+            while lines[0].startswith('#'):
+                lines.pop(0)
+            tokens = []
+            for line in lines:
+
+                parts = line.split('\t')
+                id_, word, lemma, pos, tag, morph, head, dep, _1, ner = parts
+                if '-' in id_ or '.' in id_:
+                    continue
+                try:
+                    id_ = int(id_) - 1
+                    head = (int(head) - 1) if head != '0' else id_
+                    dep = 'ROOT' if dep == 'root' else dep
+                    tag = pos if tag == '_' else tag
+                    tag = tag+'__'+morph  if use_morphology else tag
+                    ner = ner if ner else 'O'
+                    tokens.append((id_, word, tag, head, dep, ner))
+                except:
+                    print(line)
+                    raise
+            tuples = [list(t) for t in zip(*tokens)]
+            yield (None, [[tuples, []]])
+            i += 1
+            if n >= 1 and i >= n:
+                break
+
+def generate_sentence(sent):
+    (id_, word, tag, head, dep, ner) = sent
+    sentence = {}
+    tokens = []
+    ner = iob_to_biluo(ner)
+    for i, id in enumerate(id_):
+        token = {}
+        token["orth"] = word[i]
+        token["tag"] = tag[i]
+        token["head"] = head[i] - id
+        token["dep"] = dep[i]
+        token["ner"] = ner[i]
+        tokens.append(token)
+    sentence["tokens"] = tokens
+    return sentence
+
+
+def create_doc(sentences,id):
+    doc = {}
+    paragraph = {}
+    doc["id"] = id
+    doc["paragraphs"] = []
+    paragraph["sentences"] = sentences
+    doc["paragraphs"].append(paragraph)
+    return doc