如何将文档名称与两个数据集进行比较和匹配

Question

我试图做一个批上传PDF文件。他们的名字结构如下：

mm/yyyy AAA BBBB.pdf

• AAA是三个字母的PipeNameAbreviation
• BBBB是3个或3个以上的字母/数字LocationAbbreviation。

在柱塞中，您将看到用户将在视图中选择“公司”和“日期”。然后，他们将选择PDF。我需要做的是将文件的PipeNameAbr与数据库中的PipeNameAbr进行比较，然后将正确的PipeId & PipeName分配给格式数据。这将是一致的字母数，3。我还需要对Location做同样的事情，但对于格式数据需要LocationId & LocationAbr。区别在于字母/数字的长度。所以我需要与最后4个Abbreviation进行比较和匹配。

柱塞

 var regex = /^\d+\D\d+\s*?(\S*)\s*(\S*)\..*$/i;
$scope.upload = function () {
    var files = $scope.files;
    if (files && files.length) {
        for (var i = 0; i < files.length; i++) {
            var file = files[i];

            if (regex.test(file.name)) { 
                var matches = file.name.match(regex);

                    $upload.upload({
                    url: '/api/apiBatchPipeLine',
                    fields: {

                        'typeId': 1,
                        'companyId': $scope.companyId.CompanyId,
                        'documentDate': $scope.model.documentDate,
                        'pipeId': $scope.PipeId,
                        'pipeName': $scope.PipeName,
                        'locationId': $scope.LocationId,
                        'locationAb': $scope.LocationAb
                    },
                    file: file
                }).progress(function (evt) {
                    var progressPercentage = parseInt(100.0 * evt.loaded / evt.total);
                    console.log('progress: ' + progressPercentage + '% ' + evt.config.file.name);
                }).success(function (data, status, headers, config) {
                    console.log('file ' + config.file.name + 'uploaded. Response: ' +
                                JSON.stringify(data));
                }).error(function (err, result) {
                    console.log(err, result);
                });

            }

        }
    }
};

JSON

$scope.pipes = [{"$id":"1","PipeId":1,"PipeAb":"ANR","PipeName":"Transcanada ANR Pipeline","Documents":null},{"$id":"2","PipeId":2,"PipeAb":"CGT","PipeName":"Columbia Gulf Transmission","Documents":null},{"$id":"3","PipeId":3,"PipeAb":"CHA","PipeName":"Enterprise Channel Pipeline","Documents":null},{"$id":"4","PipeId":4,"PipeAb":"FGT","PipeName":"Energy Transfer Florida Gas Transmission","Documents":null},{"$id":"5","PipeId":5,"PipeAb":"GAB","PipeName":"Enbridge Garden Banks Pipeline","Documents":null},{"$id":"6","PipeId":6,"PipeAb":"GLO ","PipeName":"American Midstream Gloria  Pipeline","Documents":null},{"$id":"7","PipeId":7,"PipeAb":"GSO","PipeName":"Boardwalk Gulf South Pipeline","Documents":null},{"$id":"8","PipeId":8,"PipeAb":"HIO","PipeName":"Enterprise High Island Offshore System","Documents":null},{"$id":"9","PipeId":9,"PipeAb":"HIP","PipeName":"American Midstream High Point Pipeline","Documents":null},{"$id":"10","PipeId":10,"PipeAb":"HPL","PipeName":"Energy Transfer Houston Pipeline","Documents":null},{"$id":"11","PipeId":11,"PipeAb":"TEJ","PipeName":"Kinder Morgan Tejas Pipeline","Documents":null},{"$id":"12","PipeId":12,"PipeAb":"KIN","PipeName":"Kinetica Partners Pipeline","Documents":null},{"$id":"13","PipeId":13,"PipeAb":"NGP","PipeName":"Kinder Morgan Natural Gas Pipeline","Documents":null},{"$id":"14","PipeId":14,"PipeAb":"SER","PipeName":"Energy Transfer Sea Robin Pipeline Company ","Documents":null},{"$id":"15","PipeId":15,"PipeAb":"SNT","PipeName":"Kinder Morgan Southern Natural Gas Company","Documents":null},{"$id":"16","PipeId":16,"PipeAb":"SRY","PipeName":"MCPO Stingray Pipeline Company","Documents":null},{"$id":"17","PipeId":17,"PipeAb":"TGT","PipeName":"Kinder Morgan Tennessee Gas Pipeline","Documents":null},{"$id":"18","PipeId":18,"PipeAb":"TET","PipeName":"Spectra Energy Texas Eastern Pipeline","Documents":null},{"$id":"19","PipeId":19,"PipeAb":"TXG","PipeName":"Boardwalk Texas Gas Transmission","Documents":null},{"$id":"20","PipeId":20,"PipeAb":"TSC","PipeName":"Williams Transcontinental Gas Pipeline","Documents":null},{"$id":"21","PipeId":21,"PipeAb":"TRK","PipeName":"Energy Transfer Trunkline Gas Company","Documents":null},{"$id":"22","PipeId":22,"PipeAb":"VGS","PipeName":"Targa Venice Gathering System","Documents":null}];

JSON

 $scope.locations = [{"$id":"1","LocationId":1,"LocationAb":"BS32","LocationName":"BravoSam 32","Documents":null},{"$id":"2","LocationId":2,"LocationAb":"MP46","LocationName":"MikePier 46","Documents":null},{"$id":"3","LocationId":3,"LocationAb":"MP140","LocationName":"MikePier 140","Documents":null},{"$id":"4","LocationId":4,"LocationAb":"VR16","LocationName":"VectorRoland 16","Documents":null},{"$id":"5","LocationId":5,"LocationAb":"AP96","LocationName":"AlphaPass 96","Documents":null},{"$id":"6","LocationId":6,"LocationAb":"DZ26","LocationName":"DeltaZulu 26","Documents":null},{"$id":"7","LocationId":7,"LocationAb":"SV963","LocationName":"SandmanViper 963","Documents":null}];

我是附加一个屏幕截图，我目前正在看什么，我现在有什么。

​

用于测试的PDF名为

02-2015 HIP 02 32.pdf 02-2015 HIP MP46.pdf 02-2015 HIP MP140.pdf 02-2015 TSC VR16.pdf

我有一个正则表达式，它从pdf名称中删除日期，并分离管道和位置。我相信我需要遍历文件数组，但是什么样的循环呢？我会用开关语句来比较吗？我用数据库中的json创建了一个柱塞。

这里更新的是工作角度版本

$scope.upload = function () {
    var files = $scope.files;
    if (files && files.length) {
        for (var i = 0; i < files.length; i++) {
            var file = files[i];

            $scope.pipeLookup = {};
            $scope.locationLookup = {};
            
            $scope.pipes.map(function (pip) {
                $scope.pipeLookup[pip['PipeAb']] = pip;
            });
            $scope.locations.map(function (loc) {
                $scope.locationLookup[loc['LocationAb']] = loc;
            });

            var matches = file.name.match(/^\d+\D\d+\s*?(\S*)\s*(\S*?)\./i);

                $scope.pipe = $scope.pipeLookup[matches[1]];
                $scope.loc = $scope.locationLookup[matches[2]];

                $upload.upload({
                    url: '/api/apiBatchPipeLine',
                    fields: {

                        'typeId': 1,
                        'companyId': $scope.companyId.CompanyId,
                        'documentDate': $scope.model.documentDate,
                        'pipeId': $scope.pipe.PipeId,
                        'pipeName': $scope.pipe['PipeName'],
                        'companyName': $scope.CompanyName,
                        'locationId': $scope.loc['LocationId'],
                        'locationAb': $scope.loc['LocationAb']
                    },
                    file: file
                }).progress(function (evt) {
                    var progressPercentage = parseInt(100.0 * evt.loaded / evt.total);
                    console.log('progress: ' + progressPercentage + '% ' + evt.config.file.name);
                }).success(function (data, status, headers, config) {
                    notificationFactory.success();
                }).error(function (err, result) {
                    notificationFactory.error();
                    console.log(err, result);
                });
            
        }
    }
};

Answer 1

如果你必须与之匹配的缩略语永远是独一无二的，那么你需要做相当多的查找。您可以选择迭代JSON一次，并以一种以缩写作为关键的方式存储管道/位置：

var pipeLookup = {};
var locationLookup = {};

$scope.pipes.map(function(pip) {
    pipeLookup[pip['PipeAb']] = pip;
});
$scope.locations.map(function(loc) {
    locationLookup[loc['LocationAb']] = loc;
});

所以这里我要说的是，对于$scope.pipes的每一个条目，我都希望在pipeLookup中有一个条目，其中包含as key管道的PipeAb和value的整个管道对象。在此之后，这些Lookup变量本质上是hashmap，因此您可以很容易地使用regex匹配捕获组找到正确的管道，如下所示：

var matches = file.match(/^\d+\D\d+\s*?(\S*)\s*(\S*?)\./i);
var pipe = pipeLookup[matches[1]];
var loc = locationLookup[matches[2]];

然后，您可以使用pipe.PipeId、pipe.PipeName、loc.LocationId和任何其他可以分配给fields属性的属性。(您是否要制作这些pipeLookup和locationLookup vars属性取决于您。我对AngularJS不太熟悉)

为下面的代码片段中的每个文件名找到与正确的Pipe/Location属性匹配的简化版本。(为了简单起见，它没有AngularJS )

​

var pipes = [{"$id":"1","PipeId":1,"PipeAb":"ANR","PipeName":"Transcanada ANR Pipeline","Documents":null},{"$id":"2","PipeId":2,"PipeAb":"CGT","PipeName":"Columbia Gulf Transmission","Documents":null},{"$id":"3","PipeId":3,"PipeAb":"CHA","PipeName":"Enterprise Channel Pipeline","Documents":null},{"$id":"4","PipeId":4,"PipeAb":"FGT","PipeName":"Energy Transfer Florida Gas Transmission","Documents":null},{"$id":"5","PipeId":5,"PipeAb":"GAB","PipeName":"Enbridge Garden Banks Pipeline","Documents":null},{"$id":"6","PipeId":6,"PipeAb":"GLO ","PipeName":"American Midstream Gloria  Pipeline","Documents":null},{"$id":"7","PipeId":7,"PipeAb":"GSO","PipeName":"Boardwalk Gulf South Pipeline","Documents":null},{"$id":"8","PipeId":8,"PipeAb":"HIO","PipeName":"Enterprise High Island Offshore System","Documents":null},{"$id":"9","PipeId":9,"PipeAb":"HIP","PipeName":"American Midstream High Point Pipeline","Documents":null},{"$id":"10","PipeId":10,"PipeAb":"HPL","PipeName":"Energy Transfer Houston Pipeline","Documents":null},{"$id":"11","PipeId":11,"PipeAb":"TEJ","PipeName":"Kinder Morgan Tejas Pipeline","Documents":null},{"$id":"12","PipeId":12,"PipeAb":"KIN","PipeName":"Kinetica Partners Pipeline","Documents":null},{"$id":"13","PipeId":13,"PipeAb":"NGP","PipeName":"Kinder Morgan Natural Gas Pipeline","Documents":null},{"$id":"14","PipeId":14,"PipeAb":"SER","PipeName":"Energy Transfer Sea Robin Pipeline Company ","Documents":null},{"$id":"15","PipeId":15,"PipeAb":"SNT","PipeName":"Kinder Morgan Southern Natural Gas Company","Documents":null},{"$id":"16","PipeId":16,"PipeAb":"SRY","PipeName":"MCPO Stingray Pipeline Company","Documents":null},{"$id":"17","PipeId":17,"PipeAb":"TGT","PipeName":"Kinder Morgan Tennessee Gas Pipeline","Documents":null},{"$id":"18","PipeId":18,"PipeAb":"TET","PipeName":"Spectra Energy Texas Eastern Pipeline","Documents":null},{"$id":"19","PipeId":19,"PipeAb":"TXG","PipeName":"Boardwalk Texas Gas Transmission","Documents":null},{"$id":"20","PipeId":20,"PipeAb":"TSC","PipeName":"Williams Transcontinental Gas Pipeline","Documents":null},{"$id":"21","PipeId":21,"PipeAb":"TRK","PipeName":"Energy Transfer Trunkline Gas Company","Documents":null},{"$id":"22","PipeId":22,"PipeAb":"VGS","PipeName":"Targa Venice Gathering System","Documents":null}];
var locations = [{"$id":"1","LocationId":1,"LocationAb":"BS32","LocationName":"BravoSam 32","Documents":null},{"$id":"2","LocationId":2,"LocationAb":"MP46","LocationName":"MikePier 46","Documents":null},{"$id":"3","LocationId":3,"LocationAb":"MP140","LocationName":"MikePier 140","Documents":null},{"$id":"4","LocationId":4,"LocationAb":"VR16","LocationName":"VectorRoland 16","Documents":null},{"$id":"5","LocationId":5,"LocationAb":"AP96","LocationName":"AlphaPass 96","Documents":null},{"$id":"6","LocationId":6,"LocationAb":"DZ26","LocationName":"DeltaZulu 26","Documents":null},{"$id":"7","LocationId":7,"LocationAb":"SV963","LocationName":"SandmanViper 963","Documents":null}];

var files = ['02-2015 HIP BS32.pdf', '02-2015 HIP MP46.pdf', '02-2015 HIP MP140.pdf', '02-2015 TSC VR16.pdf'];

var pipeLookup = {};
var locationLookup = {};

pipes.map(function(pip) {
  pipeLookup[pip['PipeAb']] = pip;
});
locations.map(function(loc) {
  locationLookup[loc['LocationAb']] = loc;
});

document.getElementById('out').value = files.map(function(file) {
  var matches = file.match(/^\d+\D\d+\s*?(\S*)\s*(\S*?)\./i);
  var pipe = pipeLookup[matches[1]];
  var loc = locationLookup[matches[2]];
  return file + '\tPipeId: ' + pipe['PipeId'] +
            '\tLocationId: ' + loc['LocationId'] + 
            '\tPipeName: ' + pipe['PipeName'];
}).join('\n');

<textarea id="out" rows="10" style="width:100%"></textarea>

​

另一种方法是迭代每个文件的$scope.pipes和$scope.locations。这意味着代码可读性降低，性能下降。