Rename OCREngine to Document and move it to pixelocr.document.

pixelocr/document.py

@@ -0,0 +1,76 @@
+# Copyright (C) 2014  Andrey Golovizin
+#
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+
+import itertools
+from glob import glob
+from os import path
+
+from . import formatting
+from .image import Image
+from .page import Page, Space
+from .glyphdb import GlyphDB, SPACE, NEWLINE
+
+
+class Document(object):
+    SPACE_WIDTH = 15
+
+    def __init__(self, dirname, ui, skip=0, limit=None, output_format='text'):
+        super().__init__()
+        self.dirname = dirname
+        self.ui = ui
+        self.filenames = sorted(glob(path.join(dirname, '*.png')))[skip:skip + limit if limit else None]
+        self.glyphdb = GlyphDB(path.join(self.dirname, 'glyphdb.pickle'))
+        self.output_format = output_format
+        self.last_style = (False, False, (255, 255, 255))  # FIXME get rid of hardcoded value
+
+    def save_glyphdb(self):
+        self.glyphdb.save()
+
+    def load_page(self, filename):
+        return Page(Image.fromfile(filename), filename)
+
+    def recognize(self):
+        for filename in self.filenames:
+            page = self.load_page(filename)
+            self.ui.turn_page(page)
+            page_text = self.recognize_page(page)
+            print(page_text)
+            with open(filename + self.output_format.suffix, 'w') as page_text_file:
+                page_text_file.write(page_text)
+
+    def recognize_page(self, page):
+        glyph_data_seq = itertools.chain(*(self.recognize_line(line) for line in page.lines))
+        return ''.join(self.output_format.format(glyph_data_seq))
+
+    def recognize_line(self, line):
+        yield from [SPACE] * int(line.indent / self.SPACE_WIDTH)
+        for glyph in line.glyphs:
+            yield self.recognize_glyph(glyph)
+        yield NEWLINE
+
+    def recognize_glyph(self, glyph):
+        self.ui.process_events()
+
+        if isinstance(glyph, Space):
+            return SPACE
+        try:
+            glyph_data = self.glyphdb[glyph]
+        except KeyError:
+            text, bold, italic = self.ui.ask_for_help(glyph)
+            glyph_data = self.glyphdb.add_glyph(glyph, text, bold, italic)
+        self.last_style = glyph_data.style
+        return glyph_data
+