Merge pull request #24 from bigdata-ustc/docs

[BUILD] Initialization of the autodoc using sphinx

Author: tswsxk

.github/workflows/python-test.yml

@@ -19,7 +19,7 @@ jobs:
           python-version: ${{ matrix.python-version }}
       - name: Install dependencies
         run: |
-          pip install -e .[test]
+          pip install -e .[test,full]
           pip install codecov
       - name: Test with pytest
         run: |

.readthedocs.yml

@@ -0,0 +1,28 @@
+# .readthedocs.yml
+# Read the Docs configuration file
+# See https://docs.readthedocs.io/en/stable/config-file/v2.html for details
+
+# Required
+version: 2
+
+# Build documentation in the docs/ directory with Sphinx
+sphinx:
+  configuration: docs/source/conf.py
+
+# Build documentation with MkDocs
+#mkdocs:
+#  configuration: mkdocs.yml
+
+# Optionally build your docs in additional formats such as PDF and ePub
+formats: []
+
+# Optionally set the version of Python and requirements
+# required to build your docs
+python:
+  version: 3.7
+  install:
+    - requirements: docs/requirements.txt
+    - method: pip
+      path: .
+      extra_requirements:
+        - full

EduNLP/Formula/ast/ast.py

@@ -41,15 +41,18 @@ def ast(formula: (str, List[Dict]), index=0, forest_begin=0, father_tree=None, i
 
     Notes
     ----------
-    Some functions are not supportd in katex
-    eg :
+    Some functions are not supportd in ``katex``
+    e.g.,
+
     1. tag
-    '\\begin{equation} \\tag{tagName} F=ma \\end{equation}'
-    '\\begin{align} \\tag{1} y=x+z \\end{align}'
-    '\\tag*{hi} x+y^{2x}'
+        - ``\\begin{equation} \\tag{tagName} F=ma \\end{equation}``
+        - ``\\begin{align} \\tag{1} y=x+z \\end{align}``
+        - ``\\tag*{hi} x+y^{2x}``
     2. dddot
-    '\\frac{ \\dddot y }{ x }'
-    3. see other: https://github.com/KaTeX/KaTeX/blob/master/docs/support_table.md
+        - ``\\frac{ \\dddot y }{ x }``
+
+    For more information, refer to
+    `katex support table <https://github.com/KaTeX/KaTeX/blob/master/docs/support_table.md>`_
     """
     tree = []
     index += forest_begin

EduNLP/I2V/i2v.py

@@ -11,23 +11,24 @@
 
 
 class I2V(object):
+    """
+
+    Parameters
+    ----------
+    tokenizer: str
+        the tokenizer name
+    t2v: str
+        the name of token2vector model
+    args:
+        the parameters passed to t2v
+    tokenizer_kwargs: dict
+        the parameters passed to tokenizer
+    pretrained_t2v: bool
+    kwargs:
+        the parameters passed to t2v
+    """
     def __init__(self, tokenizer, t2v, *args, tokenizer_kwargs: dict = None, pretrained_t2v=False, **kwargs):
-        """
-
-        Parameters
-        ----------
-        tokenizer: str
-            the tokenizer name
-        t2v: str
-            the name of token2vector model
-        args:
-            the parameters passed to t2v
-        tokenizer_kwargs: dict
-            the parameters passed to tokenizer
-        pretrained_t2v: bool
-        kwargs:
-            the parameters passed to t2v
-        """
+
         self.tokenizer: Tokenizer = get_tokenizer(tokenizer, **tokenizer_kwargs if tokenizer_kwargs is not None else {})
         if pretrained_t2v:
             logger.info("Use pretrained t2v model %s" % t2v)
@@ -101,6 +102,18 @@ def from_pretrained(cls, name, model_dir=MODEL_DIR, *args, **kwargs):
 
 
 def get_pretrained_i2v(name, model_dir=MODEL_DIR):
+    """
+
+    Parameters
+    ----------
+    name
+    model_dir
+
+    Returns
+    -------
+    i2v model: I2V
+
+    """
     if name not in MODELS:
         raise KeyError(
             "Unknown model name %s, use one of the provided models: %s" % (name, ", ".join(MODELS.keys()))

EduNLP/SIF/sif.py

@@ -7,6 +7,8 @@
 from .tokenization import tokenize, link_formulas
 from .parser import Parser
 
+__all__ = ["is_sif", "to_sif", "sif4sci"]
+
 
 def is_sif(item):
     r"""

EduNLP/SIF/tokenization/text/stopwords.py

@@ -5,7 +5,7 @@
 from EduNLP.utils import abs_current_dir, path_append
 
 DEFAULT_FILEPATH = os.path.abspath(
-    path_append(abs_current_dir(__file__), "..", "..", "..", "..", "meta_data", "sif_stopwords.txt")
+    path_append(abs_current_dir(__file__), "..", "..", "..", "meta_data", "sif_stopwords.txt")
 )
 
 

EduNLP/SIF/tokenization/text/tokenization.py

@@ -7,14 +7,14 @@
 jieba.setLogLevel(logging.INFO)
 
 
-def tokenize(text, granularity="word", stopwords=DEFAULT_STOPWORDS):
+def tokenize(text, granularity="word", stopwords="default"):
     """
 
     Parameters
     ----------
     text
     granularity
-    stopwords
+    stopwords: str, None or set
 
     Returns
     -------
@@ -26,6 +26,7 @@ def tokenize(text, granularity="word", stopwords=DEFAULT_STOPWORDS):
     >>> tokenize("三角函数是基本初等函数之一", granularity="char")
     ['三', '角', '函', '数', '基', '初', '函', '数']
     """
+    stopwords = DEFAULT_STOPWORDS if stopwords == "default" else stopwords
     stopwords = stopwords if stopwords is not None else {}
     if granularity == "word":
         return [token for token in jieba.cut(text) if token not in stopwords and token.strip()]

EduNLP/SIF/tokenization/tokenization.py

@@ -15,6 +15,11 @@
 
 
 class TokenList(object):
+    """
+    Attributes
+    -------------
+
+    """
     def __init__(self, segment_list: SegmentList, text_params=None, formula_params=None, figure_params=None):
         self._tokens = []
         self._text_tokens = []

meta_data/sif_stopwords.txt renamed to EduNLP/meta_data/sif_stopwords.txt

@@ -0,0 +1 @@
+recursive-include EduNLP/meta_data *