refactor!: remove more layers of class hierarchy

playa/exceptions.py

@@ -55,6 +55,10 @@ class PDFIOError(PDFException, IOError):
     pass
 
 
+class PDFInterpreterError(PDFException):
+    pass
+
+
 class PDFNoValidXRef(PDFSyntaxError):
     pass
 
@@ -85,3 +89,11 @@ class PDFPasswordIncorrect(PDFEncryptionError):
 
 class PDFTextExtractionNotAllowed(PDFEncryptionError):
     pass
+
+
+class PDFFontError(PDFException):
+    pass
+
+
+class PDFUnicodeNotDefined(PDFFontError):
+    pass

playa/layout.py

@@ -14,7 +14,6 @@
 from playa.exceptions import PDFValueError
 from playa.pdfcolor import PDFColorSpace
 from playa.pdffont import PDFFont
-from playa.pdfinterp import Color, PDFGraphicState
 from playa.pdftypes import PDFStream
 from playa.utils import (
     INF,
@@ -31,6 +30,61 @@
 logger = logging.getLogger(__name__)
 
 
+Color = Union[
+    float,  # Greyscale
+    Tuple[float, float, float],  # R, G, B
+    Tuple[float, float, float, float],  # C, M, Y, K
+]
+
+
+class PDFGraphicState:
+    def __init__(self) -> None:
+        self.linewidth: float = 0
+        self.linecap: Optional[object] = None
+        self.linejoin: Optional[object] = None
+        self.miterlimit: Optional[object] = None
+        self.dash: Optional[Tuple[object, object]] = None
+        self.intent: Optional[object] = None
+        self.flatness: Optional[object] = None
+
+        # stroking color
+        self.scolor: Optional[Color] = None
+
+        # non stroking color
+        self.ncolor: Optional[Color] = None
+
+    def copy(self) -> "PDFGraphicState":
+        obj = PDFGraphicState()
+        obj.linewidth = self.linewidth
+        obj.linecap = self.linecap
+        obj.linejoin = self.linejoin
+        obj.miterlimit = self.miterlimit
+        obj.dash = self.dash
+        obj.intent = self.intent
+        obj.flatness = self.flatness
+        obj.scolor = self.scolor
+        obj.ncolor = self.ncolor
+        return obj
+
+    def __repr__(self) -> str:
+        return (
+            "<PDFGraphicState: linewidth=%r, linecap=%r, linejoin=%r, "
+            " miterlimit=%r, dash=%r, intent=%r, flatness=%r, "
+            " stroking color=%r, non stroking color=%r>"
+            % (
+                self.linewidth,
+                self.linecap,
+                self.linejoin,
+                self.miterlimit,
+                self.dash,
+                self.intent,
+                self.flatness,
+                self.scolor,
+                self.ncolor,
+            )
+        )
+
+
 class LTItem:
     """Interface for things that can be analyzed"""
 

playa/pdfdocument.py

@@ -13,6 +13,7 @@
     Iterable,
     Iterator,
     List,
+    Mapping,
     NamedTuple,
     Optional,
     Protocol,
@@ -27,11 +28,13 @@
 
 from playa import settings
 from playa.arcfour import Arcfour
+from playa.cmapdb import CMap, CMapBase, CMapDB
 from playa.data_structures import NameTree, NumberTree
 from playa.exceptions import (
     PSEOF,
     PDFEncryptionError,
     PDFException,
+    PDFFontError,
     PDFKeyError,
     PDFNoOutlines,
     PDFNoPageLabels,
@@ -42,7 +45,13 @@
     PDFTypeError,
     PSException,
 )
-from playa.pdfinterp import PDFResourceManager
+from playa.pdffont import (
+    PDFCIDFont,
+    PDFFont,
+    PDFTrueTypeFont,
+    PDFType1Font,
+    PDFType3Font,
+)
 from playa.pdfpage import PDFPage
 from playa.pdfparser import KEYWORD_XREF, PDFParser, PDFStreamParser
 from playa.pdftypes import (
@@ -72,6 +81,9 @@
 
 # Some predefined literals and keywords (these can be defined wherever
 # they are used as they are interned to the same objects)
+LITERAL_PDF = LIT("PDF")
+LITERAL_TEXT = LIT("Text")
+LITERAL_FONT = LIT("Font")
 LITERAL_OBJSTM = LIT("ObjStm")
 LITERAL_XREF = LIT("XRef")
 LITERAL_CATALOG = LIT("Catalog")
@@ -695,6 +707,78 @@ class OutlineItem(NamedTuple):
     se: Union[PDFObjRef, None]
 
 
+class PDFResourceManager:
+    """Repository of shared resources.
+
+    ResourceManager facilitates reuse of shared resources
+    such as fonts and images so that large objects are not
+    allocated multiple times.
+    """
+
+    def __init__(self, caching: bool = True) -> None:
+        self.caching = caching
+        self._cached_fonts: Dict[object, PDFFont] = {}
+
+    def get_procset(self, procs: Sequence[object]) -> None:
+        for proc in procs:
+            if proc is LITERAL_PDF or proc is LITERAL_TEXT:
+                pass
+            else:
+                pass
+
+    def get_cmap(self, cmapname: str, strict: bool = False) -> CMapBase:
+        try:
+            return CMapDB.get_cmap(cmapname)
+        except CMapDB.CMapNotFound:
+            if strict:
+                raise
+            return CMap()
+
+    def get_font(self, objid: object, spec: Mapping[str, object]) -> PDFFont:
+        if objid and objid in self._cached_fonts:
+            font = self._cached_fonts[objid]
+        else:
+            log.debug("get_font: create: objid=%r, spec=%r", objid, spec)
+            if settings.STRICT:
+                if spec["Type"] is not LITERAL_FONT:
+                    raise PDFFontError("Type is not /Font")
+            # Create a Font object.
+            if "Subtype" in spec:
+                subtype = literal_name(spec["Subtype"])
+            else:
+                if settings.STRICT:
+                    raise PDFFontError("Font Subtype is not specified.")
+                subtype = "Type1"
+            if subtype in ("Type1", "MMType1"):
+                # Type1 Font
+                font = PDFType1Font(spec)
+            elif subtype == "TrueType":
+                # TrueType Font
+                font = PDFTrueTypeFont(spec)
+            elif subtype == "Type3":
+                # Type3 Font
+                font = PDFType3Font(spec)
+            elif subtype in ("CIDFontType0", "CIDFontType2"):
+                # CID Font
+                font = PDFCIDFont(spec)
+            elif subtype == "Type0":
+                # Type0 Font
+                dfonts = list_value(spec["DescendantFonts"])
+                assert dfonts
+                subspec = dict_value(dfonts[0]).copy()
+                for k in ("Encoding", "ToUnicode"):
+                    if k in spec:
+                        subspec[k] = resolve1(spec[k])
+                font = self.get_font(None, subspec)
+            else:
+                if settings.STRICT:
+                    raise PDFFontError("Invalid Font spec: %r" % spec)
+                font = PDFType1Font(spec)  # FIXME: this is so wrong!
+            if objid and self.caching:
+                self._cached_fonts[objid] = font
+        return font
+
+
 class PDFDocument:
     """Representation of a PDF document on disk.
 

playa/pdffont.py

@@ -2,7 +2,6 @@
 import struct
 from io import BytesIO
 from typing import (
-    TYPE_CHECKING,
     Any,
     BinaryIO,
     Dict,
@@ -27,7 +26,14 @@
     UnicodeMap,
 )
 from playa.encodingdb import EncodingDB, name2unicode
-from playa.exceptions import PSEOF, PDFException, PDFKeyError, PDFValueError
+from playa.exceptions import (
+    PSEOF,
+    PDFException,
+    PDFFontError,
+    PDFKeyError,
+    PDFUnicodeNotDefined,
+    PDFValueError,
+)
 from playa.fontmetrics import FONT_METRICS
 from playa.pdftypes import (
     PDFStream,
@@ -49,9 +55,6 @@
 )
 from playa.utils import Matrix, Point, Rect, apply_matrix_norm, choplist, nunpack
 
-if TYPE_CHECKING:
-    from playa.pdfinterp import PDFResourceManager
-
 log = logging.getLogger(__name__)
 
 
@@ -838,14 +841,6 @@ def create_unicode_map(self) -> FileUnicodeMap:
         return unicode_map
 
 
-class PDFFontError(PDFException):
-    pass
-
-
-class PDFUnicodeNotDefined(PDFFontError):
-    pass
-
-
 LITERAL_STANDARD_ENCODING = LIT("StandardEncoding")
 LITERAL_TYPE1C = LIT("Type1C")
 
@@ -984,7 +979,7 @@ def to_unichr(self, cid: int) -> str:
 
 
 class PDFType1Font(PDFSimpleFont):
-    def __init__(self, rsrcmgr: "PDFResourceManager", spec: Mapping[str, Any]) -> None:
+    def __init__(self, spec: Mapping[str, Any]) -> None:
         try:
             self.basefont = literal_name(spec["BaseFont"])
         except KeyError:
@@ -1021,7 +1016,7 @@ def __repr__(self) -> str:
 
 
 class PDFType3Font(PDFSimpleFont):
-    def __init__(self, rsrcmgr: "PDFResourceManager", spec: Mapping[str, Any]) -> None:
+    def __init__(self, spec: Mapping[str, Any]) -> None:
         firstchar = int_value(spec.get("FirstChar", 0))
         # lastchar = int_value(spec.get('LastChar', 0))
         width_list = list_value(spec.get("Widths", [0] * 256))
@@ -1044,7 +1039,6 @@ class PDFCIDFont(PDFFont):
 
     def __init__(
         self,
-        rsrcmgr: "PDFResourceManager",
         spec: Mapping[str, Any],
         strict: bool = settings.STRICT,
     ) -> None: