Type annotations

CHANGELOG.md

@@ -8,6 +8,7 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).
 ### Added
 - Add support for PDF 2.0 (ISO 32000-2) AES-256 encryption ([#614](https://github.com/pdfminer/pdfminer.six/pull/614))
 - Support for Paeth PNG filter compression (predictor value = 4) ([#537](https://github.com/pdfminer/pdfminer.six/pull/537))
+- Type annotations ([#661](https://github.com/pdfminer/pdfminer.six/pull/661))
 
 ### Fixed
 - `KeyError` when `'Encrypt'` but not `'ID'` present in `trailer` ([#594](https://github.com/pdfminer/pdfminer.six/pull/594))

docs/source/conf.py

@@ -12,6 +12,7 @@
 
 import os
 import sys
+from typing import List
 
 import pdfminer
 
@@ -48,7 +49,7 @@
 # List of patterns, relative to source directory, that match files and
 # directories to ignore when looking for source files.
 # This pattern also affects html_static_path and html_extra_path.
-exclude_patterns = []
+exclude_patterns: List[str] = []
 
 
 # -- Options for HTML output -------------------------------------------------

mypy.ini

@@ -0,0 +1,27 @@
+[mypy]
+warn_unused_configs = True
+disallow_any_generics = True
+disallow_subclassing_any = True
+disallow_untyped_calls = True
+disallow_incomplete_defs = True
+disallow_untyped_decorators = True
+no_implicit_optional = True
+warn_redundant_casts = True
+warn_return_any = True
+no_implicit_reexport = True
+strict_equality = True
+
+# This seems impossible to turn on in a version-independent manner
+warn_unused_ignores = False
+
+[mypy-pdfminer.*]
+disallow_untyped_defs = True
+
+[mypy-cryptography.hazmat.*]
+ignore_missing_imports = True
+
+[mypy-nose.*]
+ignore_missing_imports = True
+
+[mypy-setuptools]
+ignore_missing_imports = True

pdfminer/_saslprep.py

@@ -21,10 +21,11 @@
 __all__ = ['saslprep']
 
 import stringprep
+from typing import Callable, Tuple
 import unicodedata
 
 # RFC4013 section 2.3 prohibited output.
-_PROHIBITED = (
+_PROHIBITED: Tuple[Callable[[str], bool], ...] = (
     # A strict reading of RFC 4013 requires table c12 here, but
     # characters from it are mapped to SPACE in the Map step. Can
     # normalization reintroduce them somehow?
@@ -39,7 +40,7 @@
     stringprep.in_table_c9)
 
 
-def saslprep(data: str, prohibit_unassigned_code_points=True) -> str:
+def saslprep(data: str, prohibit_unassigned_code_points: bool = True) -> str:
     """An implementation of RFC4013 SASLprep.
     :param data:
         The string to SASLprep.

pdfminer/arcfour.py

@@ -5,9 +5,12 @@
 """
 
 
+from typing import Sequence
+
+
 class Arcfour:
 
-    def __init__(self, key):
+    def __init__(self, key: Sequence[int]) -> None:
         # because Py3 range is not indexable
         s = [i for i in range(256)]
         j = 0
@@ -19,7 +22,7 @@ def __init__(self, key):
         (self.i, self.j) = (0, 0)
         return
 
-    def process(self, data):
+    def process(self, data: bytes) -> bytes:
         (i, j) = (self.i, self.j)
         s = self.s
         r = b''

pdfminer/ascii85.py

@@ -9,7 +9,7 @@
 
 
 # ascii85decode(data)
-def ascii85decode(data):
+def ascii85decode(data: bytes) -> bytes:
     """
     In ASCII85 encoding, every four bytes are encoded with five ASCII
     letters, using 85 different types of characters (as 256**4 < 85**5).
@@ -47,7 +47,7 @@ def ascii85decode(data):
 trail_re = re.compile(br'^(?:[a-f\d]{2}|\s)*([a-f\d])[\s>]*$', re.IGNORECASE)
 
 
-def asciihexdecode(data):
+def asciihexdecode(data: bytes) -> bytes:
     """
     ASCIIHexDecode filter: PDFReference v1.4 section 3.3.1
     For each pair of ASCII hexadecimal digits (0-9 and A-F or a-f), the
@@ -57,7 +57,7 @@ def asciihexdecode(data):
     the EOD marker after reading an odd number of hexadecimal digits, it
     will behave as if a 0 followed the last digit.
     """
-    def decode(x):
+    def decode(x: bytes) -> bytes:
         i = int(x, 16)
         return bytes((i,))