re-factor HTML re-hydrating, add fc-cloze rewrites

arcology-arroyo.org

@@ -251,45 +251,104 @@ import re
 from typing import Optional
 
 from arcology.key import id_to_arcology_key, file_to_arcology_key
+
+class HTMLRewriter():
+  def __init__(self, session):
+    self.res_404 = 'href="/404?missing={key}" class="dead-link"'
+    self.session = session
+
+  def replace(match):
+    raise NotImplementedError()
+
+  def re(self):
+    raise NotImplementedError()
+
+  def do(self, output_html):
+    return re.sub(self.re(), self.replace, output_html)
 #+end_src
 
-Rewriting the HTML is a pretty straightforward affair using [[https://docs.python.org/3/library/re.html#re.sub][re.sub]] with callbacks rather than static replacements. The function which accepts the match object pull the node's [[id:arcology/arroyo/key][=ARCOLOGY_KEY=]], with an optional node-id anchor attached to it. This is then farmed out to =arcology_key_to_url= to be turned in to a URL. In this fashion, each =href= is replaced with a URL that will route to the target page, or a 404 page link with a CSS class attached.
+Rewriting the HTML is a pretty straightforward affair using [[https://docs.python.org/3/library/re.html#re.sub][re.sub]] with callbacks rather than static replacements, with some abstraction sprinkled on top in the form of the =HTMLRewriter= superclass defined above. Each implementation of it provides a function which accepts the match object, and pulls the node's [[id:arcology/arroyo/key][=ARCOLOGY_KEY=]] with an optional node-id anchor attached to it. This is then farmed out to [[id:arcology/arroyo/key][=arcology_key_to_url=]] or so to be turned in to a URL. In this fashion, each =href= is replaced with a URL that will route to the target page, or a 404 page link with a CSS class attached.
 
-#+begin_src python :tangle arcology/html.py
-def rewrite_html(input_html: str, session: sqlmodel.Session) -> str:
-  """
-  Run a series of replacement functions on the input HTML and return a new string.
-  """
-  res_404 = 'href="/404?missing={key}" class="dead-link"'
+I'm pretty sure this is all quite inefficient but as always I invoke [[id:personal_software_can_be_shitty][Personal Software Can Be Shitty]].
 
-  output_html = input_html
+So ID links can be rewritten like:
 
-  def id_replacement_fn(match):
+#+begin_src python :tangle arcology/html.py
+class IDReplacementRewriter(HTMLRewriter):
+  def replace(self, match):
     id = match.group(1)
-    key = id_to_arcology_key(id, session)
+    key = id_to_arcology_key(id, self.session)
     if key is None:
-      return res_404.format(key=id)
+      return self.res_404.format(key=id)
     else:
       return 'class="internal" href="{url}"'.format(url=arcology_key_to_url(key))
 
-  output_html = re.sub(r'href="id:([^"]+)"', id_replacement_fn, output_html)
+  def re(self):
+    return r'href="id:([^"]+)"'
+#+end_src
+
+File links can be rewritten like:
 
-  def file_replacement_fn(match):
+#+begin_src python :tangle arcology/html.py
+class FileReplacementRewriter(HTMLRewriter):
+  def replace(self, match):
     file = match.group(1)
     if file is None:
-      return res_404.format(key=file)
-    key = file_to_arcology_key(file, session)
+      return self.res_404.format(key=file)
+    key = file_to_arcology_key(file, self.session)
     if key is None:
-      return res_404.format(key=file)
+      return self.res_404.format(key=file)
     else:
       return 'class="file" href="{url}"'.format(url=arcology_key_to_url(key))
 
-  output_html = re.sub(r'href="file://([^"]+)"', file_replacement_fn, output_html)
+  def re(self):
+    return r'href="file://([^"]+)"'
+#+end_src
+
+[[id:cce/org-roam][org-roam]] stub links can be rewritten link. This one is a little wonky because =res_404= and the other regexen don't only want to operate on the anchor's attribute. This one wants to strip the =roam:= text from the =[[roam:Stub]]= links.
+
+#+begin_src python :tangle arcology/html.py
+class RoamReplacementRewriter(HTMLRewriter):
+  def replace(self, match):
+    return self.res_404.format(key=match.group(1)) + ">"
+
+  def re(self):
+    return r'href="roam:([^"]+)">roam:'
+#+end_src
+
+I also make some quality-of-life rewrites of my [[id:2e31b385-a003-4369-a136-c6b78c0917e1][org-fc]] cloze cards in to simple =<span>= elements with the hint embedded in them.
+
+#+begin_src python :tangle arcology/html.py
+class FCClozeReplacementRewriter(HTMLRewriter):
+  def replace(self, match):
+    main = match.group(1) or ""
+    hint = match.group(2) or ""
+    hint = re.sub(r"</?[^>]+>", "", hint)
+    return f"<span class='fc-cloze' title='{hint}'>{main}</span>"
+  
+  def re(self):
+    return r'{{([^}]+)}{?([^}]+)?}?@[0-9]+}'
+#+end_src
 
-  def roam_replacement_fn(match):
-    return res_404.format(key=match.group(1)) + "\">"
+Invoke all these in a simple little harness:
 
-  output_html = re.sub(r'href="roam:([^"]+)" >roam:"', roam_replacement_fn, output_html)
+#+begin_src python :tangle arcology/html.py
+def rewrite_html(input_html: str, session: sqlmodel.Session) -> str:
+  """
+  Run a series of replacement functions on the input HTML and return a new string.
+  """
+
+  output_html = input_html
+
+  rewriters = [
+    IDReplacementRewriter(session),
+    FileReplacementRewriter(session),
+    RoamReplacementRewriter(session),
+    FCClozeReplacementRewriter(session),
+  ]
+
+  for rewriter in rewriters:
+    output_html = rewriter.do(output_html)
 
   return output_html
 #+end_src
@@ -579,7 +638,11 @@ Links in the [[id:cce/org-roam][org-roam]] database have a useful =type= column.
            (let ((dest-file (caar (org-roam-db-query
                                    [:select file :from nodes
                                     :where (= id $s1)]
-                                   dest))))
+                                   dest)))
+                 (source-title (caar (org-roam-db-query
+                                   [:select title :from nodes
+                                    :where (= id $s1)]
+                                   source))))
              (when (and dest-file (arcology--published-page? dest-file)
                         (arroyo-db-query [:insert :into arcology-links
                                           :values $v1]
@@ -591,6 +654,15 @@ Links in the [[id:cce/org-roam][org-roam]] database have a useful =type= column.
           (t nil))))
 #+end_src
 
+** INPROGRESS =source_title= should populate with the immediate parent header's title, not level 0
+:LOGBOOK:
+- State "INPROGRESS" from "NEXT"       [2022-08-05 Fri 14:03]
+:END:
+
+It's passed in to =arroyo-arcology--insert-links= [[id:arcology/arroyo][Below]]. Not sure the better way to do that -- query =org-roam-db= in the insert function itself? good enough for now prolly.
+
+deal with the title being fetched and populated in that function below if necessary.
+
 * Arcology Nodes
 :PROPERTIES:
 :ID:       arcology/arroyo/node

arcology/html.py

@@ -18,40 +18,79 @@ from typing import Optional
 
 from arcology.key import id_to_arcology_key, file_to_arcology_key
 
-def rewrite_html(input_html: str, session: sqlmodel.Session) -> str:
-  """
-  Run a series of replacement functions on the input HTML and return a new string.
-  """
-  res_404 = 'href="/404?missing={key}" class="dead-link"'
+class HTMLRewriter():
+  def __init__(self, session):
+    self.res_404 = 'href="/404?missing={key}" class="dead-link"'
+    self.session = session
 
-  output_html = input_html
+  def replace(match):
+    raise NotImplementedError()
 
-  def id_replacement_fn(match):
+  def re(self):
+    raise NotImplementedError()
+
+  def do(self, output_html):
+    return re.sub(self.re(), self.replace, output_html)
+
+class IDReplacementRewriter(HTMLRewriter):
+  def replace(self, match):
     id = match.group(1)
-    key = id_to_arcology_key(id, session)
+    key = id_to_arcology_key(id, self.session)
     if key is None:
-      return res_404.format(key=id)
+      return self.res_404.format(key=id)
     else:
       return 'class="internal" href="{url}"'.format(url=arcology_key_to_url(key))
 
-  output_html = re.sub(r'href="id:([^"]+)"', id_replacement_fn, output_html)
+  def re(self):
+    return r'href="id:([^"]+)"'
 
-  def file_replacement_fn(match):
+class FileReplacementRewriter(HTMLRewriter):
+  def replace(self, match):
     file = match.group(1)
     if file is None:
-      return res_404.format(key=file)
-    key = file_to_arcology_key(file, session)
+      return self.res_404.format(key=file)
+    key = file_to_arcology_key(file, self.session)
     if key is None:
-      return res_404.format(key=file)
+      return self.res_404.format(key=file)
     else:
       return 'class="file" href="{url}"'.format(url=arcology_key_to_url(key))
 
-  output_html = re.sub(r'href="file://([^"]+)"', file_replacement_fn, output_html)
+  def re(self):
+    return r'href="file://([^"]+)"'
+
+class RoamReplacementRewriter(HTMLRewriter):
+  def replace(self, match):
+    return self.res_404.format(key=match.group(1)) + ">"
+
+  def re(self):
+    return r'href="roam:([^"]+)">roam:'
+
+class FCClozeReplacementRewriter(HTMLRewriter):
+  def replace(self, match):
+    main = match.group(1) or ""
+    hint = match.group(2) or ""
+    hint = re.sub(r"</?[^>]+>", "", hint)
+    return f"<span class='fc-cloze' title='{hint}'>{main}</span>"
+  
+  def re(self):
+    return r'{{([^}]+)}{?([^}]+)?}?@[0-9]+}'
+
+def rewrite_html(input_html: str, session: sqlmodel.Session) -> str:
+  """
+  Run a series of replacement functions on the input HTML and return a new string.
+  """
+
+  output_html = input_html
 
-  def roam_replacement_fn(match):
-    return res_404.format(key=match.group(1)) + "\">"
+  rewriters = [
+    IDReplacementRewriter(session),
+    FileReplacementRewriter(session),
+    RoamReplacementRewriter(session),
+    FCClozeReplacementRewriter(session),
+  ]
 
-  output_html = re.sub(r'href="roam:([^"]+)" >roam:"', roam_replacement_fn, output_html)
+  for rewriter in rewriters:
+    output_html = rewriter.do(output_html)
 
   return output_html