sebsync 1.0b1__tar.gz → 1.0.2__tar.gz

{sebsync-1.0b1 → sebsync-1.0.2}/PKG-INFO

@@ -1,13 +1,13 @@
 Metadata-Version: 2.1
 Name: sebsync
-Version: 1.0b1
+Version: 1.0.2
 Summary: Synchronize Standard Ebooks catalog with local EPUB collection.
 Home-page: https://github.com/pbryan/sebsync/
 License: MIT
 Keywords: standard,ebook,book,synchronization,sync,download
 Author: sebsync authors
 Requires-Python: >=3.10,<4.0
-Classifier: Development Status :: 4 - Beta
+Classifier: Development Status :: 5 - Production/Stable
 Classifier: Environment :: Console
 Classifier: Intended Audience :: End Users/Desktop
 Classifier: License :: OSI Approved :: MIT License

{sebsync-1.0b1 → sebsync-1.0.2}/pyproject.toml

@@ -8,7 +8,7 @@ target-version = ['py312']
 
 [tool.poetry]
 name = "sebsync"
-version = "1.0b1"
+version = "1.0.2"
 description = "Synchronize Standard Ebooks catalog with local EPUB collection."
 readme = "README.md"
 authors = ["sebsync authors"]
@@ -16,7 +16,7 @@ homepage = "https://github.com/pbryan/sebsync/"
 license = "MIT"
 keywords = ["standard", "ebook", "book", "synchronization", "sync", "download"]
 classifiers = [
-    "Development Status :: 4 - Beta",
+    "Development Status :: 5 - Production/Stable",
     "Environment :: Console",
     "Intended Audience :: End Users/Desktop",
     "Topic :: System :: Archiving :: Mirroring",
@@ -28,9 +28,9 @@ click = "^8.1"
 requests = "^2.32"
 
 [tool.poetry.dev-dependencies]
-black = "^24.4"
+black = "^24.8"
 isort = "^5.13"
-pre-commit = "^3.7"
+pre-commit = "^3.8"
 pytest = "^8.3"
 pytest-cov = "^5.0"
 
@@ -44,3 +44,4 @@ no_sections = true
 
 [tool.poetry.scripts]
 sebsync = "sebsync:main"
+    

{sebsync-1.0b1 → sebsync-1.0.2}/sebsync.py

@@ -9,6 +9,7 @@ from dataclasses import dataclass
 from datetime import datetime, timezone
 from pathlib import Path
 from requests.auth import HTTPBasicAuth
+from urllib.parse import urlparse
 
 
 _dry_run: bool = False
@@ -20,18 +21,23 @@ class Status:
     NEW = click.style("N", fg="green")
     UPDATE = click.style("U", fg="blue")
     EXTRA = click.style("X", fg="yellow")
+    UNKNOWN = click.style("?", fg="yellow")
 
 
 _epilog = f"""
-    The following statuses are reported:
+    \b
+    Download naming conventions:
+    • standard: Standard Ebooks' naming (e.g. "edwin-a-abbott_flatland.epub")
+    • sortable: sortable author/title (e.g. "Abbott, Edwin A. - Flatland.epub")
 
     \b
-    {Status.NEW}: new (downloads the new ebook to downloads directory)
-    {Status.UPDATE}: update (overwrites the existing local ebook with new version)
-    {Status.EXTRA}: extraneous (local ebook was not found in Standard Ebooks catalog)
+    Reported file statuses:
+    • {Status.NEW}: new (downloads the new ebook to downloads directory)
+    • {Status.UPDATE}: update (overwrites the existing local ebook with new version)
+    • {Status.EXTRA}: extraneous (local ebook not found in Standard Ebooks catalog)
+    • {Status.UNKNOWN}: unknown (local ebook could not be processed)
 
-    An extraneous ebook can occur when Standard Ebooks changes the identifier of a previously
-    published ebook. It's a rare occurrence, and it's generally safe to delete such files.
+    See https://github.com/pbryan/sebsync/ for updates, bug reports and answers.
 """
 
 
@@ -99,6 +105,8 @@ def get_remote_ebooks(opds_url: str, email: str, type: str) -> dict[str, Standar
             updated=fromisoformat(entry.find("atom:updated", ns).text),
         )
         ebooks[ebook.id] = ebook
+    if not ebooks:
+        raise click.ClickException("OPDS catalog download failed. Is email address correct?")
     return ebooks
 
 
@@ -106,50 +114,76 @@ def get_local_ebooks(dir: Path) -> dict[str, LocalEbook]:
     """Return metadata of Standard EPUBs in the specified directory and subdirectories."""
     ebooks = {}
     for path in dir.glob("**/*.epub"):
-        with zipfile.ZipFile(path) as zip:
-            with zip.open("META-INF/container.xml") as file:
-                root = ElementTree.parse(file)
-                ns = {"container": "urn:oasis:names:tc:opendocument:xmlns:container"}
-                rootfile = root.find(".//container:rootfile", ns).attrib["full-path"]
-            with zip.open(rootfile) as file:
-                root = ElementTree.parse(file)
-                ns = {
-                    "opf": "http://www.idpf.org/2007/opf",
-                    "dc": "http://purl.org/dc/elements/1.1/",
-                }
-                metadata = root.find("opf:metadata", ns)
-                id = metadata.find("dc:identifier", ns)
-                if id is None or "standardebooks.org" not in id.text:
-                    continue
-                modified = metadata.find(".//opf:meta[@property='dcterms:modified']", ns)
-                ebook = LocalEbook(
-                    id=id.text,
-                    title=metadata.find(".//dc:title", ns).text,
-                    path=path,
-                    modified=fromisoformat(modified.text),
-                )
-                ebooks[ebook.id] = ebook
+        if not path.is_file():
+            continue
+        try:
+            with zipfile.ZipFile(path) as zip:
+                with zip.open("META-INF/container.xml") as file:
+                    root = ElementTree.parse(file)
+                    ns = {"container": "urn:oasis:names:tc:opendocument:xmlns:container"}
+                    rootfile = root.find(".//container:rootfile", ns).attrib["full-path"]
+                with zip.open(rootfile) as file:
+                    root = ElementTree.parse(file)
+                    ns = {
+                        "opf": "http://www.idpf.org/2007/opf",
+                        "dc": "http://purl.org/dc/elements/1.1/",
+                    }
+                    metadata = root.find("opf:metadata", ns)
+                    id = metadata.find("dc:identifier", ns)
+                    if id is None or "standardebooks.org" not in id.text:
+                        continue
+                    modified = metadata.find(".//opf:meta[@property='dcterms:modified']", ns)
+                    ebook = LocalEbook(
+                        id=id.text,
+                        title=metadata.find(".//dc:title", ns).text,
+                        path=path,
+                        modified=fromisoformat(modified.text),
+                    )
+                    ebooks[ebook.id] = ebook
+        except:
+            echo_status(path, Status.UNKNOWN)
     return ebooks
 
 
 def download_ebook(url: str, path: Path) -> None:
     """Download the ebook at the specified URL into the specified path."""
-    if not _dry_run:
-        response = requests.get(url, stream=True)
-        with path.open("wb") as file:
-            for chunk in response.iter_content(chunk_size=1 * 1024 * 1024):
-                file.write(chunk)
+    if _dry_run:
+        return
+    download = path.with_suffix(".sebsync")
+    response = requests.get(url, stream=True)
+    with download.open("wb") as file:
+        for chunk in response.iter_content(chunk_size=1 * 1024 * 1024):
+            file.write(chunk)
+    download.replace(path)
+
+
+def sortable_author(author: str) -> str:
+    """Return the sortable name of the given author."""
+    suffixes = {"Jr.", "Sr.", "Esq.", "PhD"}
+    split = author.split()
+    if len(split) < 2:
+        return author
+    last = split.pop().rstrip(",")
+    suffix = None
+    if last in suffixes:
+        suffix = last
+        last = split.pop()
+    result = last
+    if split:
+        result += f", {' '.join(split)}"
+    if suffix:
+        result += f", {suffix}"
+    return result
 
 
 def ebook_filename(ebook: StandardEbook) -> str:
-    """Return an appropriate EPUB file name for the given ebook author and title."""
+    """Return an EPUB file name for Standard ebook."""
     replace = {"/": "-", "‘": "'", "’": "'", '"': "'", "“": "'", "”": "'"}
-    author = ebook.author
-    title = ebook.title
-    names = author.split()
-    if len(names) > 1:
-        author = f"{names[-1]}, {' '.join(names[:-1])}"
-    result = f"{author} - {title}.epub"
+    match _naming:
+        case "standard":
+            result = Path(urlparse(ebook.href).path).name
+        case "sortable":
+            result = f"{sortable_author(ebook.author)} - {ebook.title}.epub"
     for k, v in replace.items():
         result = result.replace(k, v)
     return result
@@ -168,6 +202,11 @@ def ebook_filename(ebook: StandardEbook) -> str:
     type=click.Path(exists=True, file_okay=False, dir_okay=True, writable=True, path_type=Path),
     default=if_exists(Path.home() / "Downloads"),
 )
+@click.option(
+    "--force-update",
+    help="Force update of all local ebooks.",
+    is_flag=True,
+)
 @click.option(
     "--dry-run",
     help="Perform a trial run with no changes made.",
@@ -179,6 +218,12 @@ def ebook_filename(ebook: StandardEbook) -> str:
     required=True,
 )
 @click.help_option()
+@click.option(
+    "--naming",
+    type=click.Choice(["standard", "sortable"]),
+    help="Download file naming convention.",
+    default="standard",
+)
 @click.option(
     "--opds",
     help="URL of Standard Ebooks OPDS catalog.",
@@ -191,7 +236,7 @@ def ebook_filename(ebook: StandardEbook) -> str:
 )
 @click.option(
     "--type",
-    type=click.Choice(type_selector.keys()),
+    type=click.Choice(list(type_selector.keys())),
     help="EPUB type to download.",
     default="compatible",
 )
@@ -202,10 +247,12 @@ def ebook_filename(ebook: StandardEbook) -> str:
 )
 @click.version_option(package_name="sebsync")
 def sebsync(
-    books: str,
-    downloads: str,
+    books: Path,
+    downloads: Path,
     dry_run: bool,
     email: str,
+    force_update: bool,
+    naming: str,
     opds: str,
     quiet: bool,
     type: str,
@@ -214,14 +261,14 @@ def sebsync(
     global _dry_run
     global _verbose
     global _quiet
+    global _naming
 
     _dry_run = dry_run
-    _verbose = verbose and not quiet  # quiet wins
+    _naming = naming
     _quiet = quiet
+    _verbose = verbose and not quiet  # quiet wins
 
     remote_ebooks = get_remote_ebooks(opds, email, type)
-    if not remote_ebooks:
-        raise click.ClickException("OPDS download failed. Is email address correct?")
     if _verbose:
         click.echo(f"Found {len(remote_ebooks)} remote ebooks.")
 
@@ -231,7 +278,7 @@ def sebsync(
 
     for remote_ebook in remote_ebooks.values():
         if local_ebook := local_ebooks.get(remote_ebook.id):
-            if remote_ebook.updated != local_ebook.modified:
+            if remote_ebook.updated != local_ebook.modified or force_update:
                 echo_status(local_ebook.path, Status.UPDATE)
                 download_ebook(remote_ebook.href, local_ebook.path)
         else:
@@ -245,7 +292,7 @@ def sebsync(
 
 
 def main():
-    sebsync(auto_envvar_prefix="SEBSYNC", show_default=True)
+    sebsync(show_default=True)
 
 
 if __name__ == "__main__":