about summary refs log tree commit diff
path: root/.venv/lib/python3.12/site-packages/epub/utils.py
diff options
context:
space:
mode:
authorS. Solomon Darnell2025-03-28 21:52:21 -0500
committerS. Solomon Darnell2025-03-28 21:52:21 -0500
commit4a52a71956a8d46fcb7294ac71734504bb09bcc2 (patch)
treeee3dc5af3b6313e921cd920906356f5d4febc4ed /.venv/lib/python3.12/site-packages/epub/utils.py
parentcc961e04ba734dd72309fb548a2f97d67d578813 (diff)
downloadgn-ai-master.tar.gz
two version of R2R are here HEAD master
Diffstat (limited to '.venv/lib/python3.12/site-packages/epub/utils.py')
-rw-r--r--.venv/lib/python3.12/site-packages/epub/utils.py38
1 files changed, 38 insertions, 0 deletions
diff --git a/.venv/lib/python3.12/site-packages/epub/utils.py b/.venv/lib/python3.12/site-packages/epub/utils.py
new file mode 100644
index 00000000..dc3a73f3
--- /dev/null
+++ b/.venv/lib/python3.12/site-packages/epub/utils.py
@@ -0,0 +1,38 @@
+# -*- coding: utf-8 -*-
+from __future__ import unicode_literals
+
+
+def get_node_text(node):
+    """
+    Return the text content of an xml.dom Element Node.
+
+    If node does not have content, this function return an empty string.
+    """
+    text = ''
+
+    node.normalize()
+    if node.firstChild and node.firstChild.data:
+        text = node.firstChild.data.strip()
+
+    return text
+
+
+def get_urlpath_part(urlpath):
+    """
+    Return a path without url fragment (something like `#frag` at the end).
+
+    This function allow to use path from references and NCX file to read
+    item from Manifest with a correct href (without losing the fragment part).
+
+    eg.:
+
+        url = 'text/chapter1.xhtml#part2'
+        href, fragment = get_urlpath_part(url)
+        print href # 'text/chapter1.xhtml'
+        print fragment # '#part2'
+    """
+    href = urlpath
+    fragment = None
+    if urlpath.count('#'):
+        href, fragment = urlpath.split('#')
+    return (href, fragment)