|
| 1 | +/*--------------------------------------------------------------------------------------------- |
| 2 | + * Copyright (c) Microsoft Corporation. All rights reserved. |
| 3 | + * Licensed under the MIT License. See License.txt in the project root for license information. |
| 4 | + *--------------------------------------------------------------------------------------------*/ |
| 5 | + |
| 6 | +import { closeSync, openSync, readSync, statSync } from 'fs'; |
| 7 | + |
| 8 | +export const defaultTopLevelTokens = [ |
| 9 | + '"meta"', |
| 10 | + '"nodes"', |
| 11 | + '"edges"', |
| 12 | + '"trace_function_infos"', |
| 13 | + '"trace_tree"', |
| 14 | + '"samples"', |
| 15 | + '"locations"', |
| 16 | + '"strings"' |
| 17 | +]; |
| 18 | + |
| 19 | +export function formatBytes(bytes) { |
| 20 | + if (Math.abs(bytes) < 1024) { |
| 21 | + return `${bytes} B`; |
| 22 | + } |
| 23 | + if (Math.abs(bytes) < 1024 * 1024) { |
| 24 | + return `${(bytes / 1024).toFixed(1)} KB`; |
| 25 | + } |
| 26 | + return `${(bytes / 1024 / 1024).toFixed(1)} MB`; |
| 27 | +} |
| 28 | + |
| 29 | +export function findTokenOffsets(path, tokens = defaultTopLevelTokens, options = {}) { |
| 30 | + const stat = statSync(path); |
| 31 | + const fd = openSync(path, 'r'); |
| 32 | + const chunkSize = options.chunkSize ?? 8 * 1024 * 1024; |
| 33 | + const overlap = options.overlap ?? 256; |
| 34 | + const found = new Map(); |
| 35 | + let previous = Buffer.alloc(0); |
| 36 | + let position = 0; |
| 37 | + |
| 38 | + try { |
| 39 | + while (position < stat.size && found.size < tokens.length) { |
| 40 | + const toRead = Math.min(chunkSize, stat.size - position); |
| 41 | + const chunk = Buffer.allocUnsafe(toRead); |
| 42 | + const bytesRead = readSync(fd, chunk, 0, toRead, position); |
| 43 | + if (bytesRead <= 0) { |
| 44 | + break; |
| 45 | + } |
| 46 | + |
| 47 | + const combined = Buffer.concat([previous, chunk.subarray(0, bytesRead)]); |
| 48 | + |
| 49 | + for (const token of tokens) { |
| 50 | + if (found.has(token)) { |
| 51 | + continue; |
| 52 | + } |
| 53 | + |
| 54 | + const index = combined.indexOf(token); |
| 55 | + if (index !== -1) { |
| 56 | + found.set(token, position - previous.length + index); |
| 57 | + } |
| 58 | + } |
| 59 | + |
| 60 | + previous = combined.subarray(Math.max(0, combined.length - overlap)); |
| 61 | + position += bytesRead; |
| 62 | + } |
| 63 | + } finally { |
| 64 | + closeSync(fd); |
| 65 | + } |
| 66 | + |
| 67 | + return { size: stat.size, offsets: found }; |
| 68 | +} |
| 69 | + |
| 70 | +export function readRange(path, start, length) { |
| 71 | + const fd = openSync(path, 'r'); |
| 72 | + const buffer = Buffer.allocUnsafe(length); |
| 73 | + let offset = 0; |
| 74 | + |
| 75 | + try { |
| 76 | + while (offset < length) { |
| 77 | + const bytesRead = readSync(fd, buffer, offset, length - offset, start + offset); |
| 78 | + if (bytesRead === 0) { |
| 79 | + return buffer.subarray(0, offset); |
| 80 | + } |
| 81 | + offset += bytesRead; |
| 82 | + } |
| 83 | + return buffer; |
| 84 | + } finally { |
| 85 | + closeSync(fd); |
| 86 | + } |
| 87 | +} |
| 88 | + |
| 89 | +export function parseMeta(path, options = {}) { |
| 90 | + const maxBytes = options.maxBytes ?? 1024 * 1024; |
| 91 | + const buffer = readRange(path, 0, maxBytes); |
| 92 | + const metaPosition = buffer.indexOf(Buffer.from('"meta"')); |
| 93 | + if (metaPosition === -1) { |
| 94 | + throw new Error('Unable to find snapshot meta section'); |
| 95 | + } |
| 96 | + |
| 97 | + const start = buffer.indexOf(Buffer.from('{'), metaPosition); |
| 98 | + if (start === -1) { |
| 99 | + throw new Error('Unable to find snapshot meta object start'); |
| 100 | + } |
| 101 | + |
| 102 | + let depth = 0; |
| 103 | + for (let i = start; i < buffer.length; i++) { |
| 104 | + if (buffer[i] === 0x22) { |
| 105 | + i++; |
| 106 | + while (i < buffer.length) { |
| 107 | + if (buffer[i] === 0x5c) { |
| 108 | + i += 2; |
| 109 | + continue; |
| 110 | + } |
| 111 | + if (buffer[i] === 0x22) { |
| 112 | + break; |
| 113 | + } |
| 114 | + i++; |
| 115 | + } |
| 116 | + continue; |
| 117 | + } |
| 118 | + |
| 119 | + if (buffer[i] === 0x7b) { |
| 120 | + depth++; |
| 121 | + } else if (buffer[i] === 0x7d) { |
| 122 | + depth--; |
| 123 | + if (depth === 0) { |
| 124 | + return JSON.parse(buffer.subarray(start, i + 1).toString('utf8')); |
| 125 | + } |
| 126 | + } |
| 127 | + } |
| 128 | + |
| 129 | + throw new Error(`Unable to parse snapshot meta within first ${formatBytes(maxBytes)}`); |
| 130 | +} |
| 131 | + |
| 132 | +export function findArrayStart(path, tokenOffset, options = {}) { |
| 133 | + const windowSize = options.windowSize ?? 4096; |
| 134 | + const buffer = readRange(path, tokenOffset, windowSize); |
| 135 | + const bracket = buffer.indexOf(Buffer.from('[')); |
| 136 | + if (bracket === -1) { |
| 137 | + throw new Error(`Unable to find array start near offset ${tokenOffset}`); |
| 138 | + } |
| 139 | + return tokenOffset + bracket + 1; |
| 140 | +} |
| 141 | + |
| 142 | +export function streamNumberArray(path, start, end, onNumber, options = {}) { |
| 143 | + const fd = openSync(path, 'r'); |
| 144 | + const chunkSize = options.chunkSize ?? 16 * 1024 * 1024; |
| 145 | + const buffer = Buffer.allocUnsafe(chunkSize); |
| 146 | + let position = start; |
| 147 | + let number = 0; |
| 148 | + let inNumber = false; |
| 149 | + let numberIndex = 0; |
| 150 | + |
| 151 | + try { |
| 152 | + while (position < end) { |
| 153 | + const toRead = Math.min(chunkSize, end - position); |
| 154 | + const bytesRead = readSync(fd, buffer, 0, toRead, position); |
| 155 | + if (bytesRead <= 0) { |
| 156 | + break; |
| 157 | + } |
| 158 | + |
| 159 | + for (let i = 0; i < bytesRead; i++) { |
| 160 | + const code = buffer[i]; |
| 161 | + if (code >= 0x30 && code <= 0x39) { |
| 162 | + number = number * 10 + code - 0x30; |
| 163 | + inNumber = true; |
| 164 | + } else if (inNumber) { |
| 165 | + onNumber(number, numberIndex++); |
| 166 | + number = 0; |
| 167 | + inNumber = false; |
| 168 | + if (code === 0x5d) { |
| 169 | + return numberIndex; |
| 170 | + } |
| 171 | + } else if (code === 0x5d) { |
| 172 | + return numberIndex; |
| 173 | + } |
| 174 | + } |
| 175 | + |
| 176 | + position += bytesRead; |
| 177 | + } |
| 178 | + |
| 179 | + if (inNumber) { |
| 180 | + onNumber(number, numberIndex++); |
| 181 | + } |
| 182 | + return numberIndex; |
| 183 | + } finally { |
| 184 | + closeSync(fd); |
| 185 | + } |
| 186 | +} |
| 187 | + |
| 188 | +/** |
| 189 | + * Streams fixed-size tuples from a number array. |
| 190 | + * |
| 191 | + * By default, the same mutable tuple array instance is reused for each callback |
| 192 | + * invocation to avoid per-tuple allocations. Callers must not retain that array |
| 193 | + * reference after onTuple returns unless options.copyTuple is enabled. |
| 194 | + */ |
| 195 | +export function streamNumberTuples(path, start, end, tupleSize, onTuple, options = {}) { |
| 196 | + const tuple = new Array(tupleSize); |
| 197 | + const copyTuple = options.copyTuple === true; |
| 198 | + let tupleIndex = 0; |
| 199 | + let fieldIndex = 0; |
| 200 | + |
| 201 | + const numberCount = streamNumberArray(path, start, end, value => { |
| 202 | + tuple[fieldIndex++] = value; |
| 203 | + if (fieldIndex === tupleSize) { |
| 204 | + onTuple(copyTuple ? tuple.slice() : tuple, tupleIndex++); |
| 205 | + fieldIndex = 0; |
| 206 | + } |
| 207 | + }, options); |
| 208 | + |
| 209 | + if (fieldIndex !== 0) { |
| 210 | + throw new Error(`Number array ended with an incomplete tuple: ${fieldIndex}/${tupleSize}`); |
| 211 | + } |
| 212 | + |
| 213 | + return { numberCount, tupleCount: tupleIndex }; |
| 214 | +} |
| 215 | + |
| 216 | +export function parseStrings(path, stringsTokenOffset, options = {}) { |
| 217 | + const normalizedOptions = typeof options === 'number' ? { fileSize: options } : options; |
| 218 | + const fileSize = normalizedOptions.fileSize ?? statSync(path).size; |
| 219 | + const length = fileSize - stringsTokenOffset; |
| 220 | + const maxBytes = normalizedOptions.maxBytes ?? 512 * 1024 * 1024; |
| 221 | + |
| 222 | + if (length > maxBytes) { |
| 223 | + throw new Error(`Refusing to parse ${formatBytes(length)} strings section into one Buffer. Pass a larger maxBytes value only if this is intentional.`); |
| 224 | + } |
| 225 | + |
| 226 | + const buffer = readRange(path, stringsTokenOffset, length); |
| 227 | + const start = buffer.indexOf(Buffer.from('[')); |
| 228 | + if (start === -1) { |
| 229 | + throw new Error(`Unable to find strings array near offset ${stringsTokenOffset}`); |
| 230 | + } |
| 231 | + |
| 232 | + let depth = 0; |
| 233 | + for (let i = start; i < buffer.length; i++) { |
| 234 | + if (buffer[i] === 0x22) { |
| 235 | + i++; |
| 236 | + while (i < buffer.length) { |
| 237 | + if (buffer[i] === 0x5c) { |
| 238 | + i += 2; |
| 239 | + continue; |
| 240 | + } |
| 241 | + if (buffer[i] === 0x22) { |
| 242 | + break; |
| 243 | + } |
| 244 | + i++; |
| 245 | + } |
| 246 | + continue; |
| 247 | + } |
| 248 | + |
| 249 | + if (buffer[i] === 0x5b) { |
| 250 | + depth++; |
| 251 | + } else if (buffer[i] === 0x5d) { |
| 252 | + depth--; |
| 253 | + if (depth === 0) { |
| 254 | + return JSON.parse(buffer.subarray(start, i + 1).toString('utf8')); |
| 255 | + } |
| 256 | + } |
| 257 | + } |
| 258 | + |
| 259 | + throw new Error('Unable to parse strings array'); |
| 260 | +} |
0 commit comments