feat: Add atx-style markdown

Added markdown with atx style headers, can be chosen as
alternative markdown template on the cli.
The existing 'markdown' template will still default to
setext-style headers.

README.md

@@ -94,6 +94,9 @@ To output annotations in a markdown-compatible syntax (the default), do:
 papis extract --template markdown
 ```
 
+There are sub-variants of the formatter for atx-style headers, with `--template markdown-atx` (`# Headings`),
+or setext-style with `--template markdown-setext` (the default style).
+
 To instead see them in a csv syntax simply invoke:
 
 ```bash
@@ -227,7 +230,8 @@ features to be implemented:
 - [ ] allow custom colors -> tag name settings not dependent on color name existing (e.g. {"important": (1.0,0.0,0.0)})
 - [ ] `--overwrite` mode where existing annotations are not dropped but overwritten on same line of note
 - [ ] `--force` mode where we simply do not drop anything
-- [ ] `--format` option to choose from default or set up a custom formatter
+- [x] `--format` option to choose from default or set up a custom formatter 
+    - called `--template` in current implementation
 - [ ] on_add hook to extract annotations as files are added
     - needs upstream help, 'on_add' hook, and pass-through of affected documents
 

papis_extract/__init__.py

@@ -8,7 +8,10 @@ import papis.strings
 from papis.document import Document
 
 from papis_extract import extractor, exporter
-from papis_extract.formatter import Formatter, format_count, format_csv, format_markdown
+from papis_extract.formatter import (
+    Formatter,
+    formatters
+)
 
 logger = papis.logging.get_logger(__name__)
 
@@ -43,7 +46,10 @@ papis.config.register_default_settings(DEFAULT_OPTIONS)
 @click.option(
     "--template",
     "-t",
-    type=click.Choice(["markdown", "count", "csv"], case_sensitive=False),
+    type=click.Choice(
+        ["markdown", "markdown-setext", "markdown-atx", "count", "csv"],
+        case_sensitive=False,
+    ),
     help="Choose an output template to format annotations with.",
 )
 def main(
@@ -76,12 +82,7 @@ def main(
         logger.warning(papis.strings.no_documents_retrieved_message)
         return
 
-    if template == "csv":
-        formatter = format_csv
-    elif template == "count":
-        formatter = format_count
-    else:
-        formatter = format_markdown
+    formatter = formatters[template]
 
     run(documents, edit=manual, write=write, git=git, formatter=formatter)
 

papis_extract/formatter.py

@@ -5,7 +5,9 @@ from papis_extract.annotation import AnnotatedDocument
 Formatter = Callable[[list[AnnotatedDocument]], str]
 
 
-def format_markdown(docs: list[AnnotatedDocument] = []) -> str:
+def format_markdown(
+    docs: list[AnnotatedDocument] = [], atx_headings: bool = False
+) -> str:
     template = (
         "{{#tag}}#{{tag}}\n{{/tag}}"
         "{{#quote}}> {{quote}}{{/quote}} {{#page}}[p. {{page}}]{{/page}}"
@@ -16,15 +18,16 @@ def format_markdown(docs: list[AnnotatedDocument] = []) -> str:
         if not entry.annotations:
             continue
 
-        title_decoration = (
-            f"{'=' * len(entry.document.get('title', ''))}   "
-            f"{'-' * len(entry.document.get('author', ''))}"
-        )
-        output += (
-            f"{title_decoration}\n"
-            f"{entry.document['title']} - {entry.document['author']}\n"
-            f"{title_decoration}\n\n"
-        )
+        heading = f"{entry.document['title']} - {entry.document['author']}\n"
+        if atx_headings:
+            output += f"# {heading}\n"
+        else:
+            title_decoration = (
+                f"{'=' * len(entry.document.get('title', ''))}   "
+                f"{'-' * len(entry.document.get('author', ''))}"
+            )
+            output += f"{title_decoration}\n" f"{heading}" f"{title_decoration}\n\n"
+
         for a in entry.annotations:
             output += a.format(template)
             output += "\n"
@@ -34,6 +37,14 @@ def format_markdown(docs: list[AnnotatedDocument] = []) -> str:
     return output
 
 
+def format_markdown_atx(docs: list[AnnotatedDocument] = []) -> str:
+    return format_markdown(docs, atx_headings=True)
+
+
+def format_markdown_setext(docs: list[AnnotatedDocument] = []) -> str:
+    return format_markdown(docs, atx_headings=False)
+
+
 def format_count(docs: list[AnnotatedDocument] = []) -> str:
     output = ""
     for entry in docs:
@@ -72,3 +83,12 @@ def format_csv(docs: list[AnnotatedDocument] = []) -> str:
             output += "\n"
 
     return output
+
+
+formatters: dict[str, Formatter] = {
+    "count": format_count,
+    "csv": format_csv,
+    "markdown": format_markdown,
+    "markdown_atx": format_markdown_atx,
+    "markdown_setext": format_markdown_setext,
+}