🎨 Extract methods to fix lines + words

ocrd_repair_inconsistencies/ocrd_repair_inconsistencies.py

@@ -42,20 +42,9 @@ class RepairInconsistencies(Processor):
         kwargs['ocrd_tool'] = OCRD_TOOL['tools'][TOOL]
         super(RepairInconsistencies, self).__init__(*args, **kwargs)
 
-    def process(self):
+    def _fix_words(self, line):
-        for (n, input_file) in enumerate(self.input_files):
+        """Fix word order in a line"""
-            page_id = input_file.pageId or input_file.ID
-            LOG.info("INPUT FILE %i / %s", n, page_id)
-            pcgts = page_from_file(self.workspace.download_file(input_file))
-            page = pcgts.get_Page()
-
-            regions = page.get_TextRegion()
-            for region in regions:
-
-                lines = region.get_TextLine()
-                for line in lines:
 
-                    # Fix words in lines
         words = line.get_Word()
         line_text = get_text(line)
         words_text = get_text(words, ' ')
@@ -68,10 +57,9 @@ class RepairInconsistencies(Processor):
                 LOG.info('Fixing word order of line "%s"', line.id)
                 line.set_Word(sorted_words)
 
-                    words = line.get_Word()
+    def _fix_glyphs(self, word):
-                    for word in words:
+        """Fix glyph order in a word"""
 
-                        # Fix glyphs in words
         glyphs = word.get_Glyph()
         word_text = get_text(word)
         glyphs_text = get_text(glyphs, '')
@@ -84,6 +72,25 @@ class RepairInconsistencies(Processor):
                 LOG.info('Fixing glyph order of word "%s"', word.id)
                 word.set_Glyph(sorted_glyphs)
 
+    def process(self):
+        for (n, input_file) in enumerate(self.input_files):
+            page_id = input_file.pageId or input_file.ID
+            LOG.info("INPUT FILE %i / %s", n, page_id)
+            pcgts = page_from_file(self.workspace.download_file(input_file))
+            page = pcgts.get_Page()
+
+
+            regions = page.get_TextRegion()
+            for region in regions:
+
+                lines = region.get_TextLine()
+                for line in lines:
+                    self._fix_words(line)
+
+                    words = line.get_Word()
+                    for word in words:
+                        self._fix_glyphs(word)
+
             file_id = input_file.ID.replace(self.input_file_grp, self.output_file_grp)
             if file_id == input_file.ID:
                 file_id = concat_padded(self.output_file_grp, n)