Add a block anchor fallback match to diff search

This commit is contained in:
Saoud Rizwan 2024-12-19 16:20:33 -08:00
parent ead5fe9625
commit d2c85760fb

View file

@ -1,64 +1,3 @@
/**
* This function reconstructs the file content by applying a streamed diff (in a
* specialized SEARCH/REPLACE block format) to the original file content. It is designed
* to handle both incremental updates and the final resulting file after all chunks have
* been processed.
*
* The diff format is a custom structure that uses three markers to define changes:
*
* <<<<<<< SEARCH
* [Exact content to find in the original file]
* =======
* [Content to replace with]
* >>>>>>> REPLACE
*
* Behavior and Assumptions:
* 1. The file is processed chunk-by-chunk. Each chunk of `diffContent` may contain
* partial or complete SEARCH/REPLACE blocks. By calling this function with each
* incremental chunk (with `isFinal` indicating the last chunk), the final reconstructed
* file content is produced.
*
* 2. Exact Matching with Fallback:
* - For each SEARCH block, the exact text must appear in the original file after
* `lastProcessedIndex`. If it does, that portion of the original file will be replaced.
* - If no exact match is found using a plain `indexOf`, we fall back to a line-by-line
* comparison that ignores leading/trailing whitespace. This is useful if the AI-generated
* search content differs slightly in indentation or spacing from the original code.
* - If neither exact nor trimmed line-based match is found, an error is thrown.
*
* 3. Empty SEARCH Section:
* - If SEARCH is empty and the original file is empty, this indicates creating a new file
* (pure insertion).
* - If SEARCH is empty and the original file is not empty, this indicates a complete
* file replacement (the entire original content is considered matched and replaced).
*
* 4. Applying Changes:
* - Before encountering the "=======" marker, lines are accumulated as search content.
* - After "=======" and before ">>>>>>> REPLACE", lines are accumulated as replacement content.
* - Once the block is complete (">>>>>>> REPLACE"), the matched section in the original
* file is replaced with the accumulated replacement lines, and the position in the original
* file is advanced.
*
* 5. Incremental Output:
* - As soon as the match location is found and we are in the REPLACE section, each new
* replacement line is appended to the result so that partial updates can be viewed
* incrementally.
*
* 6. Partial Markers:
* - If the final line of the chunk looks like it might be part of a marker but is not one
* of the known markers, it is removed. This prevents incomplete or partial markers
* from corrupting the output.
*
* 7. Finalization:
* - Once all chunks have been processed (when `isFinal` is true), any remaining original
* content after the last replaced section is appended to the result.
* - Trailing newlines are not forcibly added. The code tries to output exactly what is specified.
*
* Errors:
* - If the search block cannot be matched exactly or with the line-trimmed fallback approach,
* an error is thrown.
*/
/**
* Attempts a line-trimmed fallback match for the given search content in the original content.
* It tries to match `searchContent` lines against a block of lines in `originalContent` starting
@ -125,6 +64,152 @@ function lineTrimmedFallbackMatch(
return false
}
/**
* Attempts to match blocks of code by using the first and last lines as anchors.
* This is a third-tier fallback strategy that helps match blocks where we can identify
* the correct location by matching the beginning and end, even if the exact content
* differs slightly.
*
* The matching strategy:
* 1. Only attempts to match blocks of 3 or more lines to avoid false positives
* 2. Extracts from the search content:
* - First line as the "start anchor"
* - Last line as the "end anchor"
* 3. For each position in the original content:
* - Checks if the next line matches the start anchor
* - If it does, jumps ahead by the search block size
* - Checks if that line matches the end anchor
* - All comparisons are done after trimming whitespace
*
* This approach is particularly useful for matching blocks of code where:
* - The exact content might have minor differences
* - The beginning and end of the block are distinctive enough to serve as anchors
* - The overall structure (number of lines) remains the same
*
* @param originalContent - The full content of the original file
* @param searchContent - The content we're trying to find in the original file
* @param startIndex - The character index in originalContent where to start searching
* @returns A tuple of [startIndex, endIndex] if a match is found, false otherwise
*/
function blockAnchorFallbackMatch(
originalContent: string,
searchContent: string,
startIndex: number,
): [number, number] | false {
const originalLines = originalContent.split("\n")
const searchLines = searchContent.split("\n")
// Only use this approach for blocks of 3+ lines
if (searchLines.length < 3) {
return false
}
// Trim trailing empty line if exists
if (searchLines[searchLines.length - 1] === "") {
searchLines.pop()
}
const firstLineSearch = searchLines[0].trim()
const lastLineSearch = searchLines[searchLines.length - 1].trim()
const searchBlockSize = searchLines.length
// Find the line number where startIndex falls
let startLineNum = 0
let currentIndex = 0
while (currentIndex < startIndex && startLineNum < originalLines.length) {
currentIndex += originalLines[startLineNum].length + 1
startLineNum++
}
// Look for matching start and end anchors
for (let i = startLineNum; i <= originalLines.length - searchBlockSize; i++) {
// Check if first line matches
if (originalLines[i].trim() !== firstLineSearch) {
continue
}
// Check if last line matches at the expected position
if (originalLines[i + searchBlockSize - 1].trim() !== lastLineSearch) {
continue
}
// Calculate exact character positions
let matchStartIndex = 0
for (let k = 0; k < i; k++) {
matchStartIndex += originalLines[k].length + 1
}
let matchEndIndex = matchStartIndex
for (let k = 0; k < searchBlockSize; k++) {
matchEndIndex += originalLines[i + k].length + 1
}
return [matchStartIndex, matchEndIndex]
}
return false
}
/**
* This function reconstructs the file content by applying a streamed diff (in a
* specialized SEARCH/REPLACE block format) to the original file content. It is designed
* to handle both incremental updates and the final resulting file after all chunks have
* been processed.
*
* The diff format is a custom structure that uses three markers to define changes:
*
* <<<<<<< SEARCH
* [Exact content to find in the original file]
* =======
* [Content to replace with]
* >>>>>>> REPLACE
*
* Behavior and Assumptions:
* 1. The file is processed chunk-by-chunk. Each chunk of `diffContent` may contain
* partial or complete SEARCH/REPLACE blocks. By calling this function with each
* incremental chunk (with `isFinal` indicating the last chunk), the final reconstructed
* file content is produced.
*
* 2. Exact Matching with Fallback:
* - For each SEARCH block, the exact text must appear in the original file after
* `lastProcessedIndex`. If it does, that portion of the original file will be replaced.
* - If no exact match is found using a plain `indexOf`, we fall back to a line-by-line
* comparison that ignores leading/trailing whitespace. This is useful if the AI-generated
* search content differs slightly in indentation or spacing from the original code.
* - If neither exact nor trimmed line-based match is found, an error is thrown.
*
* 3. Empty SEARCH Section:
* - If SEARCH is empty and the original file is empty, this indicates creating a new file
* (pure insertion).
* - If SEARCH is empty and the original file is not empty, this indicates a complete
* file replacement (the entire original content is considered matched and replaced).
*
* 4. Applying Changes:
* - Before encountering the "=======" marker, lines are accumulated as search content.
* - After "=======" and before ">>>>>>> REPLACE", lines are accumulated as replacement content.
* - Once the block is complete (">>>>>>> REPLACE"), the matched section in the original
* file is replaced with the accumulated replacement lines, and the position in the original
* file is advanced.
*
* 5. Incremental Output:
* - As soon as the match location is found and we are in the REPLACE section, each new
* replacement line is appended to the result so that partial updates can be viewed
* incrementally.
*
* 6. Partial Markers:
* - If the final line of the chunk looks like it might be part of a marker but is not one
* of the known markers, it is removed. This prevents incomplete or partial markers
* from corrupting the output.
*
* 7. Finalization:
* - Once all chunks have been processed (when `isFinal` is true), any remaining original
* content after the last replaced section is appended to the result.
* - Trailing newlines are not forcibly added. The code tries to output exactly what is specified.
*
* Errors:
* - If the search block cannot be matched exactly or with the line-trimmed fallback approach,
* an error is thrown.
*/
export async function constructNewFileContent(
diffContent: string,
originalContent: string,
@ -196,17 +281,27 @@ export async function constructNewFileContent(
searchEndIndex = exactIndex + currentSearchContent.length
} else {
// Attempt fallback line-trimmed matching
const fallbackMatch = lineTrimmedFallbackMatch(
const lineMatch = lineTrimmedFallbackMatch(
originalContent,
currentSearchContent,
lastProcessedIndex,
)
if (fallbackMatch) {
;[searchMatchIndex, searchEndIndex] = fallbackMatch
if (lineMatch) {
;[searchMatchIndex, searchEndIndex] = lineMatch
} else {
throw new Error(
`The SEARCH block:\n${currentSearchContent.trimEnd()}\n...does not match anything in the file.\nThis is likely due to differences in whitespace or line endings between the SEARCH block and the actual file. Try again with a more precise SEARCH block.\n(If you keep running into this error, you may use the write_to_file tool as a workaround.)`,
// Try block anchor fallback for larger blocks
const blockMatch = blockAnchorFallbackMatch(
originalContent,
currentSearchContent,
lastProcessedIndex,
)
if (blockMatch) {
;[searchMatchIndex, searchEndIndex] = blockMatch
} else {
throw new Error(
`The SEARCH block:\n${currentSearchContent.trimEnd()}\n...does not match anything in the file.\nThis is likely due to differences in whitespace or line endings between the SEARCH block and the actual file. Try again with a more precise SEARCH block.\n(If you keep running into this error, you may use the write_to_file tool as a workaround.)`,
)
}
}
}
}