Changeset 731

Timestamp:

05/02/06 10:57:55 (2 years ago)

Author:

mfenniak

Message:

Support inline images in PDF content streams.

Files:

• pypdf/trunk/pyPdf/pdf.py (modified) (8 diffs)
• pypdf/trunk/pyPdf/utils.py (modified) (2 diffs)

pypdf/trunk/pyPdf/pdf.py

@@ -347 +347 @@
-                cnt = 0
-                while cnt < size:
-line(
+(20
-                    offset, generation = line[:16].split(" ")
-                    offset, generation = int(offset), int(generation)
@@ -525 +525 @@
-    _mergeResources = staticmethod(_mergeResources)
-
-
+, pdf
-        if not rename:
-            return stream
-
+, pdf
-        for operands,operator in stream.operations:
-            for i in range(len(operands)):
@@ -537 +537 @@
-    _contentStreamRename = staticmethod(_contentStreamRename)
-
-
+, pdf
-        # adds a graphics state "push" and "pop" to the beginning and end
-        # of a content stream.  This isolates it from changes such as 
-        # transformation matricies.
-
+, pdf
-        stream.operations.insert(0, [[], "q"])
-        stream.operations.append([[], "Q"])
@@ -581 +581 @@
-
-        originalContent = self["/Contents"].getObject()
-
+, self.pdf
-
-        page2Content = page2['/Contents'].getObject()
-
-
+, self.pdf
+, self.pdf
-        newContentArray.append(page2Content)
-
-
+, self.pdf
-        self[NameObject('/Resources')] = newResources
-
@@ -602 +602 @@
-        content = self["/Contents"].getObject()
-        if not isinstance(content, ContentStream):
-
+, self.pdf
-        self[NameObject("/Contents")] = content.flateEncode()
-
@@ -645 +645 @@
-
-class ContentStream(DecodedStreamObject):
-
+
+
-        self.operations = []
-        # stream may be a StreamObject or an ArrayObject containing
@@ -660 +661 @@
-
-    def __parseContentStream(self, stream):
+        # file("f:\\tmp.txt", "w").write(stream.read())
+        stream.seek(0, 0)
-        operands = []
-        while True:
@@ -666 +669 @@
-                break
-            stream.seek(-1, 1)
-
-
-
-
+
+
+
+
+
+
+
+
+
+
+
-            else:
-                operands.append(readObject(stream, None))
+
+    def _readInlineImage(self, stream):
+        # begin reading just after the "BI" - begin image
+        # first read the dictionary of settings.
+        settings = DictionaryObject()
+        while True:
+            tok = readNonWhitespace(stream)
+            stream.seek(-1, 1)
+            if tok == "I":
+                # "ID" - begin of image data
+                break
+            key = readObject(stream, self.pdf)
+            tok = readNonWhitespace(stream)
+            stream.seek(-1, 1)
+            value = readObject(stream, self.pdf)
+            settings[key] = value
+        # left at beginning of ID
+        tmp = stream.read(3)
+        assert tmp[:2] == "ID"
+        data = ""
+        while True:
+            tok = stream.read(1)
+            if tok == "E":
+                next = stream.read(1)
+                if next == "I":
+                    break
+                else:
+                    stream.seek(-1, 1)
+                    data += tok
+            else:
+                data += tok
+        x = readNonWhitespace(stream)
+        stream.seek(-1, 1)
+        return {"settings": settings, "data": data}
-
-    def _getData(self):
-        newdata = StringIO()
-        for operands,operator in self.operations:
-
-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
-            newdata.write("\n")
-        return newdata.getvalue()

pypdf/trunk/pyPdf/utils.py

@@ -35 +35 @@
-__author_email__ = "mfenniak@pobox.com"
-
-
+, maxchars=None
-    txt = ""
-    while True:
@@ -42 +42 @@
-            break
-        txt += tok
+        if len(txt) == maxchars:
+            break
-    return txt
-