Merge pull request #63 from datafold/docs

Documentation at readthedocs

Author: erezsh

data_diff/database.py

@@ -132,6 +132,16 @@ def select_table_schema(self, path: DbPath) -> str:
  "Provide SQL for selecting the table schema as (name, type, date_prec, num_prec)"
  ...
 
+ @abstractmethod
+ def query_table_schema(self, path: DbPath) -> Dict[str, ColType]:
+ "Query the table for its schema for table in 'path', and return {column: type}"
+ ...
+
+ @abstractmethod
+ def parse_table_name(self, name: str) -> DbPath:
+ "Parse the given table name into a DbPath"
+ ...
+
  @abstractmethod
  def close(self):
  "Close connection(s) to the database instance. Querying will stop functioning."
@@ -157,13 +167,16 @@ class Database(AbstractDatabase):
  """Base abstract class for databases.
 
  Used for providing connection code and implementation specific SQL utilities.
+
+ Instanciated using :meth:`~data_diff.connect_to_uri`
  """
 
  DATETIME_TYPES = NotImplemented
  default_schema = NotImplemented
 
  def query(self, sql_ast: SqlOrStr, res_type: type):
- "Query the given SQL AST, and attempt to convert the result to type 'res_type'"
+ "Query the given SQL code/AST, and attempt to convert the result to type 'res_type'"
+
  compiler = Compiler(self)
  sql_code = compiler.compile(sql_ast)
  logger.debug("Running SQL (%s): %s", type(self).__name__, sql_code)
@@ -224,9 +237,9 @@ def query_table_schema(self, path: DbPath) -> Dict[str, ColType]:
  # Return a dict of form {name: type} after canonizaation
  return {row[0]: self._parse_type(*row[1:]) for row in rows}
 
- @lru_cache()
- def get_table_schema(self, path: DbPath) -> Dict[str, ColType]:
- return self.query_table_schema(path)
+ # @lru_cache()
+ # def get_table_schema(self, path: DbPath) -> Dict[str, ColType]:
+ #  return self.query_table_schema(path)
 
  def _normalize_table_path(self, path: DbPath) -> DbPath:
  if len(path) == 1:
@@ -707,6 +720,12 @@ def connect_to_uri(db_uri: str, thread_count: Optional[int] = 1) -> Database:
  thread_count determines the max number of worker threads per database,
  if relevant. None means no limit.
 
+ Parameters:
+ db_uri (str): The URI for the database to connect
+ thread_count (int, optional): Size of the threadpool. Ignored by cloud databases. (default: 1)
+
+ Note: For non-cloud databases, a low thread-pool size may be a performance bottleneck.
+
  Supported databases:
  - postgres
  - mysql

data_diff/diff_tables.py

@@ -58,26 +58,33 @@ def __len__(self):
 
 @dataclass(frozen=False)
 class TableSegment:
- """Signifies a segment of rows (and selected columns) within a table"""
+ """Signifies a segment of rows (and selected columns) within a table
+
+ Parameters:
+ database (Database): Database instance. See :meth:`connect_to_uri`
+ table_path (:data:`DbPath`): Path to table in form of a tuple. e.g. `('my_dataset', 'table_name')`
+ key_column (str): Name of the key column, which uniquely identifies each row (usually id)
+ update_column (str, optional): Name of updated column, which signals that rows changed (usually updated_at or last_update)
+ extra_columns (Tuple[str, ...], optional): Extra columns to compare
+ min_key (:data:`DbKey`, optional): Lowest key_column value, used to restrict the segment
+ max_key (:data:`DbKey`, optional): Highest key_column value, used to restrict the segment
+ min_update (:data:`DbTime`, optional): Lowest update_column value, used to restrict the segment
+ max_update (:data:`DbTime`, optional): Highest update_column value, used to restrict the segment
+
+ """
 
  # Location of table
  database: Database
  table_path: DbPath
 
- # Name of the key column, which uniquely identifies each row (usually id)
+ # Columns
  key_column: str
-
- # Name of updated column, which signals that rows changed (usually updated_at or last_update)
  update_column: str = None
-
- # Extra columns to compare
  extra_columns: Tuple[str, ...] = ()
 
- # Start/end key_column values, used to restrict the segment
+ # Restrict the segment
  min_key: DbKey = None
  max_key: DbKey = None
-
- # Start/end update_column values, used to restrict the segment
  min_update: DbTime = None
  max_update: DbTime = None
 
@@ -251,19 +258,18 @@ class TableDiffer:
  bisection search recursively to find the differences efficiently.
 
  Works best for comparing tables that are mostly the name, with minor discrepencies.
+
+ Parameters:
+ bisection_factor (int): Into how many segments to bisect per iteration.
+ bisection_threshold (int): When should we stop bisecting and compare locally (in row count).
+ threaded (bool): Enable/disable threaded diffing. Needed to take advantage of database threads.
+ max_threadpool_size (int): Maximum size of each threadpool. ``None`` means auto. Only relevant when `threaded` is ``True``.
+ There may be many pools, so number of actual threads can be a lot higher.
  """
 
- # Into how many segments to bisect per iteration
  bisection_factor: int = DEFAULT_BISECTION_FACTOR
-
- # When should we stop bisecting and compare locally (in row count)
  bisection_threshold: int = DEFAULT_BISECTION_THRESHOLD
-
- # Enable/disable threaded diffing. Needed to take advantage of database threads.
  threaded: bool = True
-
- # Maximum size of each threadpool. None = auto. Only relevant when threaded is True.
- # There may be many pools, so number of actual threads can be a lot higher.
  max_threadpool_size: Optional[int] = 1
 
  # Enable/disable debug prints
@@ -274,7 +280,12 @@ class TableDiffer:
  def diff_tables(self, table1: TableSegment, table2: TableSegment) -> DiffResult:
  """Diff the given tables.
 
- Returned value is an iterator that yield pair-tuples, representing the diff. Items can be either
+ Parameters:
+ table1 (TableSegment): The "before" table to compare. Or: source table
+ table2 (TableSegment): The "after" table to compare. Or: target table
+
+ Returns:
+ An iterator that yield pair-tuples, representing the diff. Items can be either
  ('+', columns) for items in table1 but not in table2
  ('-', columns) for items in table2 but not in table1
  Where `columns` is a tuple of values for the involved columns, i.e. (id, ...extra)

docs/Makefile

@@ -0,0 +1,20 @@
+# Minimal makefile for Sphinx documentation
+#
+
+# You can set these variables from the command line.
+SPHINXOPTS =
+SPHINXBUILD = sphinx-build
+SPHINXPROJ = data-diff
+SOURCEDIR = .
+BUILDDIR = _build
+
+# Put it first so that "make" without argument is like "make help".
+help:
+@$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
+
+.PHONY: help Makefile
+
+# Catch-all target: route all unknown targets to Sphinx using the new
+# "make mode" option. $(O) is meant as a shortcut for $(SPHINXOPTS).
+%: Makefile
+@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)

docs/conf.py

@@ -0,0 +1,188 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+#
+# Documentation build configuration file, created by
+# sphinx-quickstart on Sun Aug 16 13:09:41 2020.
+#
+# This file is execfile()d with the current directory set to its
+# containing dir.
+#
+# Note that not all possible configuration values are present in this
+# autogenerated file.
+#
+# All configuration values have a default; values that are commented out
+# serve to show the default.
+
+# If extensions (or modules to document with autodoc) are in another directory,
+# add these directories to sys.path here. If the directory is relative to the
+# documentation root, use os.path.abspath to make it absolute, like shown here.
+#
+import os
+import sys
+
+sys.path.insert(0, os.path.abspath(".."))
+sys.path.append(os.path.abspath("./_ext"))
+autodoc_member_order = "bysource"
+
+
+# -- General configuration ------------------------------------------------
+
+# If your documentation needs a minimal Sphinx version, state it here.
+#
+# needs_sphinx = '1.0'
+
+# Add any Sphinx extension module names here, as strings. They can be
+# extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
+# ones.
+extensions = [
+ "sphinx.ext.autodoc",
+ "sphinx.ext.napoleon",
+ "sphinx.ext.coverage",
+ "recommonmark",
+ "sphinx_markdown_tables",
+ "sphinx_copybutton",
+ # 'sphinx_gallery.gen_gallery'
+]
+
+# Add any paths that contain templates here, relative to this directory.
+templates_path = ["_templates"]
+
+# The suffix(es) of source filenames.
+# You can specify multiple suffix as a list of string:
+#
+# source_suffix = ['.rst', '.md']
+source_suffix = {".rst": "restructuredtext", ".md": "markdown"}
+
+
+# The master toctree document.
+master_doc = "index"
+
+# General information about the project.
+project = "data-diff"
+copyright = "Datafold"
+author = "Erez Shinan"
+
+# The version info for the project you're documenting, acts as replacement for
+# |version| and |release|, also used in various other places throughout the
+# built documents.
+#
+# The short X.Y version.
+version = ""
+# The full version, including alpha/beta/rc tags.
+release = ""
+
+# The language for content autogenerated by Sphinx. Refer to documentation
+# for a list of supported languages.
+#
+# 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
+
+# List of patterns, relative to source directory, that match files and
+# directories to ignore when looking for source files.
+# This patterns also effect to html_static_path and html_extra_path
+exclude_patterns = ["_build", "Thumbs.db", ".DS_Store"]
+
+# The name of the Pygments (syntax highlighting) style to use.
+pygments_style = "sphinx"
+
+# If true, `todo` and `todoList` produce output, else they produce nothing.
+todo_include_todos = False
+
+
+# -- Options for HTML output ----------------------------------------------
+
+# The theme to use for HTML and HTML Help pages. See the documentation for
+# a list of builtin themes.
+#
+html_theme = "sphinx_rtd_theme"
+
+# Theme options are theme-specific and customize the look and feel of a theme
+# further. For a list of options available for each theme, see the
+# documentation.
+#
+# html_theme_options = {}
+
+# Add any paths that contain custom static files (such as style sheets) here,
+# relative to this directory. They are copied after the builtin static files,
+# so a file named "default.css" will overwrite the builtin "default.css".
+html_static_path = ["_static"]
+
+html_css_files = [
+ "custom.css",
+]
+
+# Custom sidebar templates, must be a dictionary that maps document names
+# to template names.
+#
+# This is required for the alabaster theme
+# refs: http://alabaster.readthedocs.io/en/latest/installation.html#sidebars
+html_sidebars = {
+ "**": [
+ "relations.html", # needs 'show_related': True theme option to display
+ "searchbox.html",
+ ]
+}
+
+
+# -- Options for HTMLHelp output ------------------------------------------
+
+# Output file base name for HTML help builder.
+htmlhelp_basename = "datadiffdoc"
+
+
+# -- Options for LaTeX output ---------------------------------------------
+
+latex_elements = {
+ # The paper size ('letterpaper' or 'a4paper').
+ #
+ # 'papersize': 'letterpaper',
+ # The font size ('10pt', '11pt' or '12pt').
+ #
+ # 'pointsize': '10pt',
+ # Additional stuff for the LaTeX preamble.
+ #
+ # 'preamble': '',
+ # Latex figure (float) alignment
+ #
+ # 'figure_align': 'htbp',
+}
+
+# Grouping the document tree into LaTeX files. List of tuples
+# (source start file, target name, title,
+# author, documentclass [howto, manual, or own class]).
+latex_documents = [
+ (master_doc, "Datadiff.tex", "Datadiff Documentation", "Erez Shinan", "manual"),
+]
+
+
+# -- Options for manual page output ---------------------------------------
+
+# One entry per manual page. List of tuples
+# (source start file, name, description, authors, manual section).
+man_pages = [(master_doc, "Datadiff", "Datadiff Documentation", [author], 1)]
+
+
+# -- Options for Texinfo output -------------------------------------------
+
+# Grouping the document tree into Texinfo files. List of tuples
+# (source start file, target name, title, author,
+# dir menu entry, description, category)
+texinfo_documents = [
+ (
+ master_doc,
+ "Datadiff",
+ "Datadiff Documentation",
+ author,
+ "Datadiff",
+ "One line description of project.",
+ "Miscellaneous",
+ ),
+]
+
+# -- Sphinx gallery config -------------------------------------------
+
+# sphinx_gallery_conf = {
+# 'examples_dirs': ['../examples'],
+# 'gallery_dirs': ['examples'],
+# }