假设我有一个目录foo,其中有一些子目录。这些子目录中的每个子目录都有0到5个可变长度的文件,我希望处理这些文件。我的初始代码如下所示:
pool.query(`
SET SEARCH_PATH TO public,os_local;
`).then(() => fs.readdirSync(srcpath)
.filter(file => fs.lstatSync(path.join(srcpath, file)).isDirectory())
.map(dir => {
fs.access(`${srcpath + dir}/${dir}_Building.shp`, fs.constants.R_OK, (err) => {
if (!err) {
openShapeFile(`${srcpath + dir}/${dir}_Building.shp`).then((source) => source.read()
.then(function dbWrite (result) {
if (result.done) {
console.log(`done ${dir}`)
} else {
const query = `INSERT INTO os_local.buildings(geometry,
id,
featcode,
version)
VALUES(os_local.ST_GeomFromGeoJSON($1),
$2,
$3,
$4) ON CONFLICT (id) DO UPDATE SET
featcode=$3,
geometry=os_local.ST_GeomFromGeoJSON($1),
version=$4;`
return pool.connect().then(client => {
client.query(query, [geoJson.split('"[[').join('[[').split(']]"').join(']]'),
result.value.properties.ID,
result.value.properties.FEATCODE,
version
]).then((result) => {
return source.read().then(dbWrite)
}).catch((err) => {
console.log(err,
query,
geoJson.split('"[[').join('[[').split(']]"').join(']]'),
result.value.properties.ID,
result.value.properties.FEATCODE,
version
)
return source.read().then(dbWrite)
})
client.release()
})
}
})).catch(err => console.log('No Buildings', err))
}
})
fs.access(`${srcpath + dir}/${dir}__ImportantBuilding.shp`, fs.constants.R_OK, (err) => {
//read file one line at a time
//spin up connection in pg.pool, insert data
})
fs.access(`${srcpath + dir}/${dir}_Road.shp`, fs.constants.R_OK, (err) => {
//read file one line at a time
//spin up connection in pg.pool, insert data
})
fs.access(`${srcpath + dir}/${dir}_Glasshouse.shp`, fs.constants.R_OK, (err) => {
//read file one line at a time
//spin up connection in pg.pool, insert data
})
fs.access(`${srcpath + dir}/${dir}_RailwayStation.shp`, fs.constants.R_OK, (err) => {
//read file one line at a time
//spin up connection in pg.pool, insert data
})
})
这在很大程度上是可行的,但它最终不得不等待每个子目录中最长的文件被完全处理,导致在实践中总是只有一个数据库连接。
有没有一种方法可以重新设计,以便更好地利用我的计算资源,同时限制活动postgres连接的数量,并强制代码等待,直到连接可用?(我在node-postgres的pg poolConfig中将它们设置为20 )
发布于 2017-06-19 05:26:29
如果您需要在一定时间内轮流处理您的文件,那么您可以使用Streams、timers(用于调度)和process.nextTick()。nodejs中有用于理解流的great manual。
发布于 2017-06-27 02:12:06
下面是一个使用生成器获取目录内容的示例。您可以立即开始获取第一对文件,然后使用异步代码并行处理文件。
// Dependencies
const fs = require('fs');
const path = require('path');
// The generator function (note the asterisk)
function* getFilesInDirectory(fullPath, recursive = false) {
// Convert file names to full paths
let contents = fs.readdirSync(fullPath).map(file => {
return path.join(fullPath, file);
});
for(let i = 0; i < contents.length; i++) {
const childPath = contents[i];
let stats = fs.statSync(childPath);
if (stats.isFile()) {
yield childPath;
} else if (stats.isDirectory() && recursive) {
yield* getFilesInDirectory(childPath, true);
}
}
}
用法:
function handleResults(results) {
... // Returns a promise
}
function processFile(file) {
... // Returns a promise
}
var files = getFilesInDirectory(__dirname, true);
var result = files.next();
var promises = [];
while(!result.done) {
console.log(result.value);
file = files.next();
// Process files in parallel
var promise = processFile(file).then(handleResults);
promises.push(promise);
}
promise.all(promises).then() {
console.log(done);
}
https://stackoverflow.com/questions/44619434
复制相似问题