apunkt/webclaw
1
0
Fork 0
mirror of https://github.com/0xMassi/webclaw.git synced 2026-07-24 07:31:01 +02:00
Code Issues Projects Releases Packages Wiki Activity

fix(cli): also fix --diff/--brand for single-row --urls-file (review)

Browse source 
Independent review found the backfill ran AFTER the --diff-with and --brand
gates, so single-row --urls-file + --diff/--brand still hit 'no input'.
Move the collect_urls + backfill before all mode gates so a one-line file
behaves like a positional URL everywhere. --watch now reuses the shared
entries instead of re-collecting (avoids double-counting the backfilled URL).
Verified: --brand single-row no longer errors; 37 tests pass, clippy clean.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
Valerio 2026-07-22 17:47:23 +02:00
parent 7f63d2f17a
commit 36cde1d488
1 changed files with 15 additions and 21 deletions
Download patch file Download diff file Expand all files Collapse all files

36
crates/webclaw-cli/src/main.rs
View file

@ -2779,6 +2779,20 @@ async fn main() {
return;
}
// Collect URLs from args + --urls-file up front, and backfill a lone
// --urls-file URL into cli.urls so a one-line file behaves like a positional
// URL across ALL modes below (crawl / watch / diff / brand / batch / single).
// See issue #86 — the mode gates and single path read cli.urls, which is
// empty when the URL came only from --urls-file.
let entries = match collect_urls(&cli) {
Ok(u) => u,
Err(e) => {
eprintln!("error: {e}");
process::exit(1);
}
};
backfill_single_file_url(&mut cli.urls, &entries);
// --crawl: recursive crawl mode
if cli.crawl {
if let Err(e) = run_crawl(&cli).await {
@ -2790,13 +2804,7 @@ async fn main() {
// --watch: poll URL(s) for changes
if cli.watch {
let watch_urls: Vec<String> = match collect_urls(&cli) {
Ok(entries) => entries.into_iter().map(|(url, _)| url).collect(),
Err(e) => {
eprintln!("error: {e}");
process::exit(1);
}
};
let watch_urls: Vec<String> = entries.iter().map(|(url, _)| url.clone()).collect();
if let Err(e) = run_watch(&cli, &watch_urls).await {
eprintln!("error: {e}");
process::exit(1);
@ -2831,20 +2839,6 @@ async fn main() {
return;
}
// Collect all URLs from args + --urls-file
let entries = match collect_urls(&cli) {
Ok(u) => u,
Err(e) => {
eprintln!("error: {e}");
process::exit(1);
}
};
// A single URL sourced only from --urls-file must behave like a positional
// URL (issue #86): the batch gates below require len > 1, and the single
// path reads cli.urls, so a one-line file would otherwise hit "no input".
backfill_single_file_url(&mut cli.urls, &entries);
// LLM modes: --extract-json, --extract-prompt, --summarize
// When multiple URLs are provided, run batch LLM extraction over all of them.
if has_llm_flags(&cli) {