Move per-thread processing stuff into Thread

[paperdoorknob] / glowfic.py

diff --git a/glowfic.py b/glowfic.py
index 9d863c887e2992cd8bbdbc4d1a8a1ddffce65155..ef71eef019e8005b4c2bbf8a34ab49b0362f3e85 100644 (file)
--- a/glowfic.py
+++ b/glowfic.py
@@ -9,7 +9,7 @@ from dataclasses import dataclass
 import itertools
 from urllib.parse import parse_qsl, urlencode, urljoin, urlparse, urlunparse
 
-from typing import Iterable
+from typing import Any, Iterable
 
 from bs4 import BeautifulSoup
 from bs4.element import Tag
@@ -19,6 +19,10 @@ from spec import Spec
 from texify import Texifier
 
 
+def ilen(it: Iterable[Any]) -> int:
+    return sum(1 for _ in it)
+
+
 def _removeViewFromURL(url: str) -> str:
     u = urlparse(url)
     old_qs = parse_qsl(u.query)
@@ -73,6 +77,7 @@ class Thread:
         self._next_thread = find_next_thread(
             BeautifulSoup(spec.htmlfilter(html), 'html.parser'))
         self._dom = BeautifulSoup(spec.htmlfilter(flat_html), 'html.parser')
+        self._spec = spec
 
     def title(self) -> str | None:
         span = self._dom.findChild("span", id="post-title")
@@ -98,6 +103,20 @@ class Thread:
 
         return itertools.chain([text()], the_replies())
 
+    def emit(self) -> None:
+        self._spec.log('Counting chunks...\r')
+        num_chunks = ilen(self.chunkDOMs())
+        title = self.title() or "chunk"
+        for i, r in enumerate(self.chunkDOMs()):
+            percent = 100.0 * i / num_chunks
+            self._spec.log(
+                f'Processing {title} {i} of {num_chunks} ({percent:.1f}%)\r')
+            self._spec.domfilter(r)
+            chunk = makeChunk(r, self._spec.images)
+            self._spec.texout.write(
+                self._spec.texfilter(renderChunk(self._spec.texifier, chunk)))
+        self._spec.log('')
+
 
 def makeChunk(chunk_dom: Tag, image_store: ImageStore) -> Chunk: