refactor(generateCommitMessageFromGitDiff.ts): rename mergeStrings to mergeDiffs and add maxDiffLength parameter

feat(generateCommitMessageFromGitDiff.ts): split file diffs into changes in files if they exceed the maximum token count
The mergeStrings function was renamed to mergeDiffs to better reflect its purpose. The function now takes an additional parameter, maxDiffLength, which is used to split file diffs into changes in files if they exceed the maximum token count. This change improves the efficiency of the function and reduces the number of tokens used.
This commit is contained in:
di-sukharev
2023-03-29 10:44:45 +08:00
parent 4cc73208cd
commit e128cdece1

View File

@@ -4,7 +4,7 @@ import {
} from 'openai';
import { api } from './api';
import { getConfig } from './commands/config';
import { mergeStrings } from './utils/mergeStrings';
import { mergeDiffs } from './utils/mergeDiffs';
import { i18n, I18nLocals } from './i18n';
import { tokenCount } from './utils/tokenCount';
@@ -14,45 +14,38 @@ const translation = i18n[(config?.language as I18nLocals) || 'en'];
const INIT_MESSAGES_PROMPT: Array<ChatCompletionRequestMessage> = [
{
role: ChatCompletionRequestMessageRoleEnum.System,
content: `You are to act as the author of a commit message in git. Your mission is to create clean and comprehensive commit messages in the conventional commit convention. I'll send you an output of 'git diff --staged' command, and you convert it into a commit message.
${
config?.emoji
? 'Use Gitmoji convention to preface the commit'
: 'Do not preface the commit with anything'
}.
${
config?.description
? 'Add a short description of why the commit is done after the commit message. Don\'t start it with "This commit", just describe the changes'
: "Don't add any descriptions to the commit, only commit message"
}.
Use the present tense.
Lines must not be longer 74 characters.
Use ${translation.localLanguage} to answer.`
// prettier-ignore
content: `You are to act as the author of a commit message in git. Your mission is to create clean and comprehensive commit messages in the conventional commit convention and explain why a change was done. I'll send you an output of 'git diff --staged' command, and you convert it into a commit message.
${config?.emoji? 'Use Gitmoji convention to preface the commit.': 'Do not preface the commit with anything.'}
${config?.description ? 'Add a short description of why the commit is done after the commit message. Don\'t start it with "This commit", just describe the changes.': "Don't add any descriptions to the commit, only commit message."}
Use the present tense. Lines must not be longer than 74 characters. Use ${translation.localLanguage} to answer.`
},
{
role: ChatCompletionRequestMessageRoleEnum.User,
content: `diff --git a/src/server.ts b/src/server.ts
index ad4db42..f3b18a9 100644
--- a/src/server.ts
+++ b/src/server.ts
@@ -10,7 +10,7 @@ import {
initWinstonLogger();
const app = express();
-const port = 7799;
+const PORT = 7799;
app.use(express.json());
@@ -34,6 +34,6 @@ app.use((_, res, next) => {
// ROUTES
app.use(PROTECTED_ROUTER_URL, protectedRouter);
-app.listen(port, () => {
- console.log(\`Server listening on port \${port}\`);
+app.listen(process.env.PORT || PORT, () => {
+ console.log(\`Server listening on port \${PORT}\`);
});`
index ad4db42..f3b18a9 100644
--- a/src/server.ts
+++ b/src/server.ts
@@ -10,7 +10,7 @@
import {
initWinstonLogger();
const app = express();
-const port = 7799;
+const PORT = 7799;
app.use(express.json());
@@ -34,6 +34,6 @@
app.use((_, res, next) => {
// ROUTES
app.use(PROTECTED_ROUTER_URL, protectedRouter);
-app.listen(port, () => {
- console.log(\`Server listening on port \${port}\`);
+app.listen(process.env.PORT || PORT, () => {
+ console.log(\`Server listening on port \${PORT}\`);
});`
},
{
role: ChatCompletionRequestMessageRoleEnum.Assistant,
@@ -96,7 +89,10 @@ export const generateCommitMessageWithChatCompletion = async (
): Promise<string | GenerateCommitMessageError> => {
try {
if (tokenCount(diff) >= MAX_REQ_TOKENS) {
const commitMessagePromises = getCommitMsgsPromisesFromFileDiffs(diff);
const commitMessagePromises = getCommitMsgsPromisesFromFileDiffs(
diff,
MAX_REQ_TOKENS
);
const commitMessages = await Promise.all(commitMessagePromises);
@@ -116,22 +112,28 @@ export const generateCommitMessageWithChatCompletion = async (
}
};
function getMessagesPromisesByLines(fileDiff: string, separator: string) {
const lineSeparator = '\n@@';
const [fileHeader, ...fileDiffByLines] = fileDiff.split(lineSeparator);
function getMessagesPromisesByChangesInFile(
fileDiff: string,
separator: string,
maxChangeLength: number
) {
const hunkHeaderSeparator = '@@ ';
const [fileHeader, ...fileDiffByLines] = fileDiff.split(hunkHeaderSeparator);
// merge multiple line-diffs into 1 to save tokens
const mergedLines = mergeStrings(
fileDiffByLines.map((line) => lineSeparator + line),
MAX_REQ_TOKENS
const mergedChanges = mergeDiffs(
fileDiffByLines.map((line) => hunkHeaderSeparator + line),
maxChangeLength
);
const lineDiffsWithHeader = mergedLines.map(
(d) => fileHeader + lineSeparator + d
const lineDiffsWithHeader = mergedChanges.map(
(change) => fileHeader + change
);
const commitMsgsFromFileLineDiffs = lineDiffsWithHeader.map((d) => {
const messages = generateCommitMessageChatCompletionPrompt(separator + d);
const commitMsgsFromFileLineDiffs = lineDiffsWithHeader.map((lineDiff) => {
const messages = generateCommitMessageChatCompletionPrompt(
separator + lineDiff
);
return api.generateCommitMessage(messages);
});
@@ -139,20 +141,27 @@ function getMessagesPromisesByLines(fileDiff: string, separator: string) {
return commitMsgsFromFileLineDiffs;
}
function getCommitMsgsPromisesFromFileDiffs(diff: string) {
export function getCommitMsgsPromisesFromFileDiffs(
diff: string,
maxDiffLength: number
) {
const separator = 'diff --git ';
const diffByFiles = diff.split(separator).slice(1);
// merge multiple files-diffs into 1 prompt to save tokens
const mergedFilesDiffs = mergeStrings(diffByFiles, MAX_REQ_TOKENS);
const mergedFilesDiffs = mergeDiffs(diffByFiles, maxDiffLength);
const commitMessagePromises = [];
for (const fileDiff of mergedFilesDiffs) {
if (tokenCount(fileDiff) >= MAX_REQ_TOKENS) {
if (tokenCount(fileDiff) >= maxDiffLength) {
// if file-diff is bigger than gpt context — split fileDiff into lineDiff
const messagesPromises = getMessagesPromisesByLines(fileDiff, separator);
const messagesPromises = getMessagesPromisesByChangesInFile(
fileDiff,
separator,
maxDiffLength
);
commitMessagePromises.push(...messagesPromises);
} else {