Merge pull request 'Link to images in RSS output' (#4) from eloitor/microblog.py:rss_1 into rss_1

Reviewed-on: #4

example/Makefile

@@ -21,7 +21,8 @@ settings:
 
 .PHONY: clean
 clean: 
-	rm ./pages/*.html 
-	rm ./tags/*/*.html 
-	rm ./webring/*.html 
-	rmdir ./pages ./tags/* ./tags ./webring
+	- rm -f ./pages/*.html 
+	- rm -f ./tags/*/*.html 
+	- rm -f ./webring/*.html 
+	- rm -f ./feeds/*.xml
+	- rmdir ./pages ./tags/* ./tags ./webring ./feeds

example/settings.toml

@@ -85,3 +85,4 @@ title="Your Microblog Title Here"
 title_tagged = "#{__tagname__} on {__title__}"
 url = "https://yourdomain.tld/microblog/"
 description = "Your description here."
+trailing_punctuation = ".,)!?>];:"

src/microblog.py

@@ -549,6 +549,8 @@ if __name__ == "__main__":
         updated = []
         updated += writepage(tpl, tl, tc, cfg["page"], 
             paginate=True if new_posts is None else False)
+        cfg["rss"]["accepted_images"] = cfg["post"]["accepted_images"]
+        cfg["rss"]["gallery_path"] = cfg["post"]["gallery"]["path_to_fullsize"]
         if cfg["rss"]["enabled"]:
             # ensure output directory for feeds exists
             if not os.path.exists("feeds"):

src/rss.py

@@ -2,6 +2,8 @@ from microblog import My_Html_Parser
 # from html.parser import HTMLParser
 from html import escape
 import sys, traceback, dateutil.parser
+from urllib.parse import urljoin
+
 try:
     import feedgenerator
 except ImportError:
@@ -11,7 +13,7 @@ except ImportError:
     print("\trss disabled - missing dependency", file=sys.stderr)
     print("\tYour microblog still may have been generated.", file=sys.stderr)
 
-def line2words(lines, limit):
+def line2words(lines, limit, trailing_punctuation):
     output = []
     char_count = 0
     break_outer_loop = False
@@ -29,15 +31,22 @@ def line2words(lines, limit):
     # last char of last word
     last_char = output[-1].strip()[-1]
     # print(output[-1], file=sys.stderr)
-    punctuation = [".", ")", ",", "!", "?", ">", ']']
-    if last_char not in punctuation:
+    if last_char not in trailing_punctuation:
         output.append("...")
     return output
 
+def _is_image_token(token: str, extensions):
+    parts = token.rsplit('.', 1)
+    return len(parts) == 2 and parts[1] in extensions
+
 # this is similar to the markup function in microblog
-def enrich_msg(lines, is_atom=True):
-    if not is_atom:
-        return lines
+def enrich_msg(
+    lines,
+    accepted_images=[],
+    gallery_path="",
+    trailing_punctuation="",
+    desc_len_limit=-1,
+):
     content = []
     parser = My_Html_Parser([])
     for line in lines:
@@ -47,6 +56,7 @@ def enrich_msg(lines, is_atom=True):
             words = line.split()
             for i in range(len(words)):
                 word  = words[i]
+                core = word.rstrip(trailing_punctuation)
                 if word.find("src=") == 0 \
                 or word.find("href=") == 0:
                     continue
@@ -54,6 +64,12 @@ def enrich_msg(lines, is_atom=True):
                     w = escape(word)
                     new_word = ("<a href=\"%s\">%s</a>") % (w, w)
                     words[i] = new_word
+                elif _is_image_token(core, accepted_images):
+                    suffix = word[len(core):]
+                    abs_url = urljoin(gallery_path, core)
+                    anchor = f"<a href=\"{escape(abs_url)}\">{escape(abs_url)}</a>"
+                    new_word = anchor + suffix
+                    words[i] = new_word
             words.insert(0,"<p>")
             words.append("</p>")
             content.append(" ".join(words))
@@ -95,12 +111,18 @@ def write_feed(posts, filename, params, tagname=None):
         # len of post.message is number of lines
         msg = post.message
         ti = " ".join(
-            line2words(msg,TITLE_LEN_LIMIT))
-        if params["use_atom"]:
-            de = " ".join(enrich_msg(msg))
-        else:
-            de = " ".join(
-                line2words(msg,DESC_LEN_LIMIT))
+            line2words(msg, TITLE_LEN_LIMIT, params["trailing_punctuation"]))
+        de = " ".join(
+            enrich_msg(
+                msg,
+                gallery_path=urljoin(
+                    params["url"], params.get("gallery_path", "") + "/"
+                ),
+                accepted_images=params["accepted_images"],
+                trailing_punctuation=params["trailing_punctuation"],
+                desc_len_limit=DESC_LEN_LIMIT,
+            )
+        )
         li = base_url + ("#%i" % post.num)
         p = dateutil.parser.parse(post.timestamp)
         if params["use_atom"]: