Add --no-page-labels switch to ignore page labels in markdown output

Fixes issue #65

pdfannots/cli.py

@@ -16,6 +16,7 @@
     'group_highlights_by_color',
     'print_filename',
     'sections',
+    'use_page_labels',
     'wrap_column',
 ]
 """Names of arguments passed to the markdown printer."""
@@ -74,6 +75,8 @@ def parse_args() -> typ.Tuple[argparse.Namespace, LAParams]:
                          ', '.join(GroupedMarkdownPrinter.ALL_SECTIONS)))
     g.add_argument("--no-condense", dest="condense", default=True, action="store_false",
                    help="Emit annotations as a blockquote regardless of length.")
+    g.add_argument("--no-page-labels", dest="use_page_labels", default=True, action="store_false",
+                   help="Ignore page labels if present, just print 1-based page numbers.")
     g.add_argument("--print-filename", dest="print_filename", default=False, action="store_true",
                    help="Print the name of each file with annotations.")
     g.add_argument("-w", "--wrap", dest="wrap_column", metavar="COLS", type=int,

pdfannots/printer/markdown.py

@@ -89,12 +89,14 @@ def __init__(
         print_filename: bool = False,             # Whether to print file names
         group_highlights_by_color: bool = False,  # Whether to group highlights by color
         remove_hyphens: bool = True,              # Whether to remove hyphens across a line break
+        use_page_labels: bool = True,             # Whether to use page labels
         wrap_column: typ.Optional[int] = None,    # Column at which output is word-wrapped
         **kwargs: typ.Any                         # Other args, ignored
     ) -> None:
         self.print_filename = print_filename
         self.group_highlights_by_color = group_highlights_by_color
         self.remove_hyphens = remove_hyphens
+        self.use_page_labels = use_page_labels
         self.wrap_column = wrap_column
         self.condense = condense
 
@@ -139,10 +141,11 @@ def print_file(
     @staticmethod
     def format_pos(
         pos: Pos,
-        document: Document
+        document: Document,
+        use_page_label: bool
     ) -> str:
 
-        result = str(pos.page).title()
+        result = pos.page.pretty_name(use_label=use_page_label).title()
 
         o = document.nearest_outline(pos)
         if o:
@@ -229,7 +232,7 @@ def format_annot(
 
         # compute the formatted position (and extra bit if needed) as a label
         assert annot.pos is not None
-        label = self.format_pos(annot.pos, document) + \
+        label = self.format_pos(annot.pos, document, self.use_page_labels) + \
             (" " + extra if extra else "") + ":"
 
         # If we have short (few words) text with a short or no comment, and the

pdfannots/types.py

@@ -131,7 +131,10 @@ def __repr__(self) -> str:
         return '<Page #%d>' % self.pageno  # zero-based page index
 
     def __str__(self) -> str:
-        if self.label:
+        return self.pretty_name()
+
+    def pretty_name(self, use_label=True) -> str:
+        if self.label and use_label:
             return 'page %s' % self.label
         else:
             # + 1 for 1-based page numbers in normal program output (error messages, etc.)