0xrsydn/idx-cli
1
mirror of https://github.com/0xrsydn/idx-cli.git synced 2026-11-07 09:45:36 +00:00
Code Issues Projects Releases 1 Packages Wiki Activity

fix(core): a row with no parsed cells rejects the page too

Browse source 
Every piece of the table body that holds a row must parse as nine cells;
ranks count the rows read, not the pieces. A rank-1 row without its cell
ends was skipped and ranks 2-10 still matched (Codex re-review).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01V3syn2fN2LNo5pvTSqc6eh
This commit is contained in:
hermes 2026-10-18 11:56:25 +00:00
commit 106590d151
1 changed files with 19 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

24
crates/idx-core/src/api/ipot/parse.rs
View file

@ -176,12 +176,14 @@ pub fn parse_broker_summary(html: &str) -> Result<IpotPage, IdxError> {
// another shape, a rank out of order, or a broker after a side's blank // another shape, a rank out of order, or a broker after a side's blank
// rows rejects the page. // rows rejects the page.
let (mut buyers_ended, mut sellers_ended) = (false, false); let (mut buyers_ended, mut sellers_ended) = (false, false);
for (index, row) in html[body_start..body_end].split("</tr>").enumerate() { let mut rank = 0;
let row = cells(row); for piece in html[body_start..body_end].split("</tr>") {
if row.is_empty() { // Only the space after the last row has no row in it.
if !piece.contains("<tr") && !piece.contains("<td") {
continue; continue;
} }
let rank = index as u32 + 1; let row = cells(piece);
rank += 1;
if row.len() != 9 || row[4].text.parse::<u32>().ok() != Some(rank) { if row.len() != 9 || row[4].text.parse::<u32>().ok() != Some(rank) {
return Err(IdxError::ParseError(format!( return Err(IdxError::ParseError(format!(
"ipot broker summary: unexpected row {rank} ({} cells, rank {:?})", "ipot broker summary: unexpected row {rank} ({} cells, rank {:?})",
@ -349,7 +351,19 @@ mod tests {
1, 1,
); );
let gap = DAY.replacen(">XL<", "><", 1); let gap = DAY.replacen(">XL<", "><", 1);
for page in [short_row, skipped_rank, gap, "</tbody><tbody>".to_string()] { // Rank 1 without its cell ends parses to no cells at all.
let body = DAY.find("<tbody>").unwrap();
let first_row_end = body + DAY[body..].find("</tr>").unwrap();
let unclosed = DAY[..body].to_string()
+ &DAY[body..first_row_end].replace("</td>", "")
+ &DAY[first_row_end..];
for page in [
short_row,
skipped_rank,
gap,
unclosed,
"</tbody><tbody>".to_string(),
] {
assert!( assert!(
matches!(parse_broker_summary(&page), Err(IdxError::ParseError(_))), matches!(parse_broker_summary(&page), Err(IdxError::ParseError(_))),
"{}", "{}",