From 38fae60b8beaf9c7b37c65325d2d285e62b6cb85 Mon Sep 17 00:00:00 2001
From: jvoisin
Date: Fri, 18 May 2018 23:52:40 +0200
Subject: Rename some files to simplify packaging

- the `src` folder is now `libmat2`
- the `main.py` script is now `mat2.py`
---
 libmat2/pdf.py | 135 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 135 insertions(+)
 create mode 100644 libmat2/pdf.py

(limited to 'libmat2/pdf.py')

diff --git a/libmat2/pdf.py b/libmat2/pdf.py
new file mode 100644
index 0000000..5b99192
--- /dev/null
+++ b/libmat2/pdf.py
@@ -0,0 +1,135 @@
+""" Handle PDF
+
+"""
+
+import os
+import re
+import logging
+import tempfile
+import io
+
+import cairo
+import gi
+gi.require_version('Poppler', '0.18')
+from gi.repository import Poppler, GLib
+
+from . import abstract
+
+logging.basicConfig(level=logging.DEBUG)
+
+
+class PDFParser(abstract.AbstractParser):
+    mimetypes = {'application/pdf', }
+    meta_list = {'author', 'creation-date', 'creator', 'format', 'keywords',
+                 'metadata', 'mod-date', 'producer', 'subject', 'title',
+                 'viewer-preferences'}
+
+    def __init__(self, filename):
+        super().__init__(filename)
+        self.uri = 'file://' + os.path.abspath(self.filename)
+        self.__scale = 2  # how much precision do we want for the render
+        try:  # Check now that the file is valid, to avoid surprises later
+            Poppler.Document.new_from_file(self.uri, None)
+        except GLib.GError:  # Invalid PDF
+            raise ValueError
+
+    def remove_all_lightweight(self):
+        """
+            Load the document into Poppler, render pages on a new PDFSurface.
+        """
+        document = Poppler.Document.new_from_file(self.uri, None)
+        pages_count = document.get_n_pages()
+
+        tmp_path = tempfile.mkstemp()[1]
+        pdf_surface = cairo.PDFSurface(tmp_path, 10, 10)
+        pdf_context = cairo.Context(pdf_surface)  # context draws on the surface
+
+        for pagenum in range(pages_count):
+            logging.info("Rendering page %d/%d", pagenum + 1, pages_count)
+            page = document.get_page(pagenum)
+            page_width, page_height = page.get_size()
+            pdf_surface.set_size(page_width, page_height)
+            pdf_context.save()
+            page.render_for_printing(pdf_context)
+            pdf_context.restore()
+            pdf_context.show_page()  # draw pdf_context on pdf_surface
+        pdf_surface.finish()
+
+        self.__remove_superficial_meta(tmp_path, self.output_filename)
+        os.remove(tmp_path)
+
+        return True
+
+    def remove_all(self):
+        """
+            Load the document into Poppler, render pages on PNG,
+            and shove those PNG into a new PDF.
+        """
+        document = Poppler.Document.new_from_file(self.uri, None)
+        pages_count = document.get_n_pages()
+
+        _, tmp_path = tempfile.mkstemp()
+        pdf_surface = cairo.PDFSurface(tmp_path, 32, 32)  # resized later anyway
+        pdf_context = cairo.Context(pdf_surface)
+
+        for pagenum in range(pages_count):
+            page = document.get_page(pagenum)
+            page_width, page_height = page.get_size()
+            logging.info("Rendering page %d/%d", pagenum + 1, pages_count)
+
+            img_surface = cairo.ImageSurface(cairo.FORMAT_ARGB32, int(page_width) * self.__scale, int(page_height) * self.__scale)
+            img_context = cairo.Context(img_surface)
+
+            img_context.scale(self.__scale, self.__scale)
+            page.render_for_printing(img_context)
+            img_context.show_page()
+
+            buf = io.BytesIO()
+            img_surface.write_to_png(buf)
+            img_surface.finish()
+            buf.seek(0)
+
+            img = cairo.ImageSurface.create_from_png(buf)
+            pdf_surface.set_size(page_width*self.__scale, page_height*self.__scale)
+            pdf_context.set_source_surface(img, 0, 0)
+            pdf_context.paint()
+            pdf_context.show_page()
+
+        pdf_surface.finish()
+
+        # Removes metadata added by Poppler
+        self.__remove_superficial_meta(tmp_path, self.output_filename)
+        os.remove(tmp_path)
+
+        return True
+
+    @staticmethod
+    def __remove_superficial_meta(in_file: str, out_file: str) -> bool:
+        document = Poppler.Document.new_from_file('file://' + in_file)
+        document.set_producer('')
+        document.set_creator('')
+        document.set_creation_date(-1)
+        document.save('file://' + os.path.abspath(out_file))
+        return True
+
+
+    @staticmethod
+    def __parse_metadata_field(data: str) -> dict:
+        metadata = {}
+        for (_, key, value) in re.findall(r"<(xmp|pdfx|pdf|xmpMM):(.+)>(.+)</\1:\2>", data, re.I):
+            metadata[key] = value
+        return metadata
+
+    def get_meta(self):
+        """ Return a dict with all the meta of the file
+        """
+        metadata = {}
+        document = Poppler.Document.new_from_file(self.uri, None)
+
+        for key in self.meta_list:
+            if document.get_property(key):
+                metadata[key] = document.get_property(key)
+        if 'metadata' in metadata:
+            parsed_meta = self.__parse_metadata_field(metadata['metadata'])
+            return {**metadata, **parsed_meta}
+        return metadata
-- 
cgit v1.3