I am dealing with a type of ASCII file where there are effectively 4 columns of data and the each row is assigned to a line in the file. Below is an example of a row of data from this file
'STOP.F 11966.0000:STOP DEPTH'
The data is always structured so that the delimiter between the first and second column is a period, the delimiter between the second and third column is a space and the delimiter between the third and fourth column is a colon.
Ideally, I would like to find a way to return the following result from the string above
['STOP', 'F', '11966.0000', 'STOP DEPTH']
I tried using a regular expression with the period, space and colon as delimiters, but it breaks down (see example below) because I don't know how to specify the specific order in which to split the string, and I don't know if there is a way to specify the maximum number of splits per delimiter right in the regular expression itself. I want it to split the delimiters in the specific order and each delimiter a maximum of 1 time.
import re
line = 'STOP.F 11966.0000:STOP DEPTH'
re.split("[. :]", line)
>>> ['STOP', 'F', '11966', '0000', 'STOP', 'DEPTH']
Any suggestions on a tidy way to do this?
答案 0 :(得分：1)
这可能有用。归功于Juan
import re
pattern = re.compile(r'^(.+)\.(.+) (.+):(.+)$')
line = 'STOP.F 11966.0000:STOP DEPTH'
pattern.search(line).groups()
Out[6]: ('STOP', 'F', '11966.0000', 'STOP DEPTH')
答案 1 :(得分：0)
/**
* NPM Module dependencies.
*/
const express = require('express');
const photoRoute = express.Router();
const multer = require('multer');
var storage = multer.memoryStorage()
var upload = multer({ storage: storage, limits: { fields: 1, fileSize: 6000000, files: 1, parts: 2 }});
const mongodb = require('mongodb');
const MongoClient = require('mongodb').MongoClient;
const ObjectID = require('mongodb').ObjectID;
let db;
/**
* NodeJS Module dependencies.
*/
const { Readable } = require('stream');
/**
* Create Express server && Routes configuration.
*/
const app = express();
app.use('/photos', photoRoute);
/**
* Connect Mongo Driver to MongoDB.
*/
MongoClient.connect('mongodb://localhost/photoDB', (err, database) => {
if (err) {
console.log('MongoDB Connection Error. Please make sure that MongoDB is running.');
process.exit(1);
}
db = database;
});
/**
* GET photo by ID Route
*/
photoRoute.get('/:photoID', (req, res) => {
try {
var photoID = new ObjectID(req.params.photoID);
} catch(err) {
return res.status(400).json({ message: "Invalid PhotoID in URL parameter. Must be a single String of 12 bytes or a string of 24 hex characters" });
}
let bucket = new mongodb.GridFSBucket(db, {
bucketName: 'photos'
});
let downloadStream = bucket.openDownloadStream(photoID);
downloadStream.on('data', (chunk) => {
res.write(chunk);
});
downloadStream.on('error', () => {
res.sendStatus(404);
});
downloadStream.on('end', () => {
res.end();
});
});
/**
* POST photo Route
*/
photoRoute.post('/', (req, res) => {
upload.single('photo')(req, res, (err) => {
if (err) {
return res.status(400).json({ message: "Upload Request Validation Failed" });
} else if(!req.body.name) {
return res.status(400).json({ message: "No photo name in request body" });
}
let photoName = req.body.name;
// Covert buffer to Readable Stream
const readablePhotoStream = new Readable();
readablePhotoStream.push(req.file.buffer);
readablePhotoStream.push(null);
let bucket = new mongodb.GridFSBucket(db, {
bucketName: 'photos'
});
let uploadStream = bucket.openUploadStream(photoName);
let id = uploadStream.id;
readablePhotoStream.pipe(uploadStream);
uploadStream.on('error', () => {
return res.status(500).json({ message: "Error uploading file" });
});
uploadStream.on('finish', () => {
return res.status(201).json({ message: "File uploaded successfully, stored under Mongo ObjectID: " + id });
});
});
});
app.listen(3005, () => {
console.log("App listening on port 3005!");
});
解决方案：
re.split()输出：
import re
s = 'STOP.F 11966.0000:STOP DEPTH'
result = re.split(r'(?<=^[^.]+)\.|(?<=^[^ ]+) |:', s)
print(result)