general progress on annotations

 * finish utils
 * annotate more of pdfinterp, pdfdevice
 * document reason for # type: ignore comments
 * fix cyclic imports
 * satisfy flake8

pdfminer/converter.py

@@ -1,17 +1,18 @@
 import io
 import logging
-from pdfminer.pdftypes import PDFStream
+from pdfminer.pdfcolor import PDFColorSpace
 from typing import List
-from pdfminer.pdfpage import PDFPage
 import re
 import sys
 
 from . import utils
-from .layout import LTChar, LTLayoutContainer
+from .layout import LAParams
+from .layout import LTChar
 from .layout import LTContainer
 from .layout import LTCurve
 from .layout import LTFigure
 from .layout import LTImage
+from .layout import LTLayoutContainer
 from .layout import LTLine
 from .layout import LTPage
 from .layout import LTRect
@@ -21,9 +22,13 @@
 from .layout import LTTextGroup
 from .layout import LTTextLine
 from .pdfdevice import PDFTextDevice
-from .pdffont import PDFFont, PDFUnicodeNotDefined
-from .pdfinterp import PDFResourceManager
-from .utils import Matrix, Rect, apply_matrix_pt
+from .pdffont import PDFFont
+from .pdffont import PDFUnicodeNotDefined
+from .pdfinterp import PDFGraphicState, PDFResourceManager
+from .pdfpage import PDFPage
+from .pdftypes import PDFStream
+from .utils import Matrix, Rect
+from .utils import apply_matrix_pt
 from .utils import bbox2str
 from .utils import enc
 from .utils import mult_matrix
@@ -35,7 +40,8 @@ class PDFLayoutAnalyzer(PDFTextDevice):
     cur_item: LTLayoutContainer
     ctm: Matrix
 
-    def __init__(self, rsrcmgr: PDFResourceManager, pageno=1, laparams=None):
+    def __init__(self, rsrcmgr: PDFResourceManager, pageno: int = 1,
+                 laparams: LAParams = None):
         PDFTextDevice.__init__(self, rsrcmgr)
         self.pageno = pageno
         self.laparams = laparams
@@ -79,7 +85,8 @@ def render_image(self, name: str, stream: PDFStream) -> None:
         self.cur_item.add(item)
         return
 
-    def paint_path(self, gstate, stroke, fill, evenodd, path):
+    def paint_path(self, gstate: PDFGraphicState, stroke, fill, evenodd, path
+                   ) -> None:
         """Paint paths described in section 4.4 of the PDF reference manual"""
         shape = ''.join(x[0] for x in path)
 
@@ -130,8 +137,9 @@ def paint_path(self, gstate, stroke, fill, evenodd, path):
                                 gstate.scolor, gstate.ncolor)
                 self.cur_item.add(curve)
 
-    def render_char(self, matrix: Matrix, font: PDFFont, fontsize, scaling, rise, cid, ncs,
-                    graphicstate):
+    def render_char(self, matrix: Matrix, font: PDFFont, fontsize: float,
+                    scaling: float, rise: float, cid: int, ncs: PDFColorSpace,
+                    graphicstate: PDFGraphicState) -> float:
         try:
             text = font.to_unichr(cid)
             assert isinstance(text, str), str(type(text))

pdfminer/layout.py

@@ -1,16 +1,22 @@
 import heapq
 import logging
-from pdfminer.pdftypes import PDFStream
-from typing import Any, Dict, Generic, Iterable, Iterator, List, Optional, Sequence, Set, Tuple, TypeVar
+from typing import (Any, Dict, Generic, Iterable, Iterator, List, Optional,
+                    Sequence, Set, Tuple, TypeVar, cast)
 
-from .utils import INF, Matrix, Rect
+from .utils import INF
+from .utils import Matrix
+from .utils import Rect
 from .utils import Plane
 from .utils import apply_matrix_pt
 from .utils import bbox2str
 from .utils import fsplit
 from .utils import get_bound
 from .utils import matrix2str
 from .utils import uniq
+from .pdfcolor import PDFColorSpace
+from .pdftypes import PDFStream
+from .pdfinterp import PDFGraphicState
+from .pdffont import PDFFont
 
 logger = logging.getLogger(__name__)
 
@@ -282,8 +288,9 @@ def get_text(self) -> str:
 class LTChar(LTComponent, LTText):
     """Actual letter in the text as a Unicode string."""
 
-    def __init__(self, matrix: Matrix, font, fontsize, scaling, rise,
-                 text: str, textwidth, textdisp, ncs, graphicstate):
+    def __init__(self, matrix: Matrix, font: PDFFont, fontsize, scaling, rise,
+                 text: str, textwidth, textdisp, ncs: PDFColorSpace,
+                 graphicstate: PDFGraphicState):
         LTText.__init__(self)
         self._text = text
         self.matrix = matrix
@@ -335,8 +342,10 @@ def is_compatible(self, obj: Any) -> bool:
         """Returns True if two characters can coexist in the same line."""
         return True
 
+
 LTContainerElement = TypeVar('LTContainerElement', LTItem, LTComponent)
 
+
 class LTContainer(LTComponent, Generic[LTContainerElement]):
     """Object that can be extended and analyzed"""
 
@@ -430,7 +439,8 @@ def add(self, obj: LTComponent) -> None:
         LTTextLine.add(self, obj)
         return
 
-    def find_neighbors(self, plane: Plane, ratio: float) -> List["LTTextLineHorizontal"]:
+    def find_neighbors(self, plane: Plane, ratio: float
+                       ) -> List["LTTextLineHorizontal"]:
         """
         Finds neighboring LTTextLineHorizontals in the plane.
 
@@ -486,7 +496,8 @@ def add(self, obj: LTComponent) -> None:
         LTTextLine.add(self, obj)
         return
 
-    def find_neighbors(self, plane: Plane, ratio: float) -> List["LTTextLineVertical"]:
+    def find_neighbors(self, plane: Plane, ratio: float
+                       ) -> List["LTTextLineVertical"]:
         """
         Finds neighboring LTTextLineVerticals in the plane.
 
@@ -600,7 +611,8 @@ def __init__(self, bbox: Rect):
         return
 
     # group_objects: group text object to textlines.
-    def group_objects(self, laparams: LAParams, objs: Iterable[LTComponent]) -> Iterator[LTTextLine]:
+    def group_objects(self, laparams: LAParams, objs: Iterable[LTComponent]
+                      ) -> Iterator[LTTextLine]:
         obj0 = None
         line = None
         for obj1 in objs:
@@ -670,11 +682,13 @@ def group_objects(self, laparams: LAParams, objs: Iterable[LTComponent]) -> Iter
             obj0 = obj1
         if line is None:
             line = LTTextLineHorizontal(laparams.word_margin)
-            line.add(obj0)  # type: ignore
+            assert obj0 is not None
+            line.add(obj0)
         yield line
         return
 
-    def group_textlines(self, laparams: LAParams, lines: Iterable[LTTextLine]) -> Iterator[LTTextBox]:
+    def group_textlines(self, laparams: LAParams, lines: Iterable[LTTextLine]
+                        ) -> Iterator[LTTextBox]:
         """Group neighboring lines to textboxes"""
         plane = Plane(self.bbox)
         plane.extend(lines)
@@ -705,7 +719,8 @@ def group_textlines(self, laparams: LAParams, lines: Iterable[LTTextLine]) -> It
                 yield box
         return
 
-    def group_textboxes(self, laparams: LAParams, boxes: Sequence[LTTextBox]) -> List[LTTextGroup]:
+    def group_textboxes(self, laparams: LAParams, boxes: Sequence[LTTextBox]
+                        ) -> List[LTTextGroup]:
         """Group textboxes hierarchically.
 
         Get pair-wise distances, via dist func defined below, and then merge
@@ -724,7 +739,7 @@ def group_textboxes(self, laparams: LAParams, boxes: Sequence[LTTextBox]) -> Lis
         :return: a list that has only one element, the final top level group.
         """
 
-        def dist(obj1:LTComponent, obj2:LTComponent) -> float:
+        def dist(obj1: LTComponent, obj2: LTComponent) -> float:
             """A distance function between two TextBoxes.
 
             Consider the bounding rectangle for obj1 and obj2.
@@ -752,7 +767,8 @@ def isany(obj1: LTComponent, obj2: LTComponent) -> Set[LTComponent]:
             objs = set(plane.find((x0, y0, x1, y1)))
             return objs.difference((obj1, obj2))
 
-        dists: List[Tuple[bool, float, int, int, LTTextContainer, LTTextContainer]] = []
+        dists: List[Tuple[bool, float, int, int, LTTextContainer,
+                          LTTextContainer]] = []
         for i in range(len(boxes)):
             box1 = boxes[i]
             for j in range(i+1, len(boxes)):
@@ -817,7 +833,8 @@ def getkey(box):
                 group.analyze(laparams)
                 assigner.run(group)
             textboxes.sort(key=lambda box: box.index)
-        self._objs = textboxes + otherobjs + empties
+        self._objs = (cast(List[LTComponent], textboxes) + otherobjs
+                      + cast(List[LTComponent], empties))
         return
 
 

pdfminer/pdfcolor.py

@@ -1,4 +1,5 @@
 import collections
+from typing import Dict
 from .psparser import LIT
 
 
@@ -9,7 +10,7 @@
 
 class PDFColorSpace:
 
-    def __init__(self, name, ncomponents):
+    def __init__(self, name: str, ncomponents: int):
         self.name = name
         self.ncomponents = ncomponents
         return
@@ -19,7 +20,7 @@ def __repr__(self):
                (self.name, self.ncomponents)
 
 
-PREDEFINED_COLORSPACE = collections.OrderedDict()
+PREDEFINED_COLORSPACE: Dict[str, PDFColorSpace] = collections.OrderedDict()
 
 for (name, n) in [
     ('DeviceGray', 1),  # default value first