apr144-bam
Version:
Parser for BAM and BAM index (bai) files
124 lines • 4.79 kB
JavaScript
import { unzip } from '@gmod/bgzf-filehandle';
import { Buffer } from 'buffer';
import BamFile, { BAM_MAGIC } from './bamFile';
import { parseHeaderText } from './sam';
async function concat(arr, opts) {
const res = await Promise.all(arr.map(async (chunk) => {
const { url, headers } = chunk;
if (url.startsWith('data:')) {
return Buffer.from(url.split(',')[1], 'base64');
}
else {
//remove referer header, it is not even allowed to be specified
// @ts-expect-error
const { referer, ...rest } = headers;
const res = await fetch(url, {
...opts,
headers: { ...opts === null || opts === void 0 ? void 0 : opts.headers, ...rest },
});
if (!res.ok) {
throw new Error(`HTTP ${res.status} fetching ${url}: ${await res.text()}`);
}
return Buffer.from(await res.arrayBuffer());
}
}));
return Buffer.concat(await Promise.all(res.map(elt => unzip(elt))));
}
export default class HtsgetFile extends BamFile {
constructor(args) {
super({ htsget: true });
this.baseUrl = args.baseUrl;
this.trackId = args.trackId;
}
async *streamRecordsForRange(chr, min, max, opts) {
var _a;
const base = `${this.baseUrl}/${this.trackId}`;
const url = `${base}?referenceName=${chr}&start=${min}&end=${max}&format=BAM`;
const chrId = (_a = this.chrToIndex) === null || _a === void 0 ? void 0 : _a[chr];
if (chrId === undefined) {
yield [];
}
else {
const result = await fetch(url, { ...opts });
if (!result.ok) {
throw new Error(`HTTP ${result.status} fetching ${url}: ${await result.text()}`);
}
const data = await result.json();
const uncba = await concat(data.htsget.urls.slice(1), opts);
yield* this._fetchChunkFeatures([
// fake stuff to pretend to be a Chunk
{
buffer: uncba,
_fetchedSize: undefined,
bin: 0,
compareTo() {
return 0;
},
toUniqueString() {
return `${chr}_${min}_${max}`;
},
fetchedSize() {
return 0;
},
minv: {
dataPosition: 0,
blockPosition: 0,
compareTo: () => 0,
},
maxv: {
dataPosition: Number.MAX_SAFE_INTEGER,
blockPosition: 0,
compareTo: () => 0,
},
toString() {
return `${chr}_${min}_${max}`;
},
},
], chrId, min, max, opts);
}
}
async _readChunk({ chunk }) {
if (!chunk.buffer) {
throw new Error('expected chunk.buffer in htsget');
}
return { data: chunk.buffer, cpositions: [], dpositions: [], chunk };
}
async getHeader(opts = {}) {
const url = `${this.baseUrl}/${this.trackId}?referenceName=na&class=header`;
const result = await fetch(url, opts);
if (!result.ok) {
throw new Error(`HTTP ${result.status} fetching ${url}: ${await result.text()}`);
}
const data = await result.json();
const uncba = await concat(data.htsget.urls, opts);
if (uncba.readInt32LE(0) !== BAM_MAGIC) {
throw new Error('Not a BAM file');
}
const headLen = uncba.readInt32LE(4);
const headerText = uncba.toString('utf8', 8, 8 + headLen);
const samHeader = parseHeaderText(headerText);
// use the @SQ lines in the header to figure out the
// mapping between ref ref ID numbers and names
const idToName = [];
const nameToId = {};
const sqLines = samHeader.filter(l => l.tag === 'SQ');
for (const [refId, sqLine] of sqLines.entries()) {
let refName = '';
let length = 0;
for (const item of sqLine.data) {
if (item.tag === 'SN') {
refName = item.value;
}
else if (item.tag === 'LN') {
length = +item.value;
}
}
nameToId[refName] = refId;
idToName[refId] = { refName, length };
}
this.chrToIndex = nameToId;
this.indexToChr = idToName;
return samHeader;
}
}
//# sourceMappingURL=htsget.js.map