Skip to content

Fix: Split single lines exceeding chunk_size limit #10

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
echobt wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Fix: Split single lines exceeding chunk_size limit #10

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
68 changes: 66 additions & 2 deletions src/core/indexer.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -342,7 +342,39 @@ impl Indexer {
let mut char_count = 0;

for (line_idx, line) in lines.iter().enumerate() {
let line_len = line.len() + 1;
let line_len = line.len() + 1; // +1 for newline

// If the line itself is larger than chunk size, we need to split it
if line_len > self.chunk_size {
// First flush current chunk if not empty
if !current_chunk.is_empty() {
chunks.push(FileChunk {
content: current_chunk.clone(),
start_line: chunk_start_line as i32,
end_line: (line_idx - 1) as i32,
});
current_chunk.clear();
char_count = 0;
}

// Now split the long line
let mut start = 0;
while start < line.len() {
let end = std::cmp::min(start + self.chunk_size, line.len());
let part = &line[start..end];

chunks.push(FileChunk {
content: part.to_string() + "\n",
start_line: line_idx as i32,
end_line: line_idx as i32,
});
start = end;
}

// After processing a forced split, reset start line for next regular accumulation
chunk_start_line = line_idx + 1;
continue;
}

if char_count + line_len > self.chunk_size && !current_chunk.is_empty() {
chunks.push(FileChunk {
Expand Down Expand Up @@ -718,7 +750,39 @@ impl ServerIndexer {
let mut char_count = 0;

for (line_idx, line) in lines.iter().enumerate() {
let line_len = line.len() + 1;
let line_len = line.len() + 1; // +1 for newline

// If the line itself is larger than chunk size, we need to split it
if line_len > self.chunk_size {
// First flush current chunk if not empty
if !current_chunk.is_empty() {
chunks.push(FileChunk {
content: current_chunk.clone(),
start_line: chunk_start_line as i32,
end_line: (line_idx - 1) as i32,
});
current_chunk.clear();
char_count = 0;
}

// Now split the long line
let mut start = 0;
while start < line.len() {
let end = std::cmp::min(start + self.chunk_size, line.len());
let part = &line[start..end];

chunks.push(FileChunk {
content: part.to_string() + "\n",
start_line: line_idx as i32,
end_line: line_idx as i32,
});
start = end;
}

// After processing a forced split, reset start line for next regular accumulation
chunk_start_line = line_idx + 1;
continue;
}

if char_count + line_len > self.chunk_size && !current_chunk.is_empty() {
chunks.push(FileChunk {
Expand Down
Loading