Get all occurrences of value in between two patterns in JavaScript-CodePudding

I have to the following long string. How do I extract all the values that are in between "url=" and "," so that I then have the following array?

"load("@bazel_tools//tools/build_defs/repo:http.bzl","http_jar")definclude_java_deps():http_jar(name="com_google_inject_guice",sha256="b378ffc35e7f7125b3c5f3a461d4591ae1685e3c781392f0c854ed7b7581d6d2",url="https://repo1.maven.org/maven2/com/google/inject/guice/4.0/guice-4.0.jar",)http_jar(name="org_sonatype_sisu_inject_cglib",sha256="42e1dfb26becbf1a633f25b47e39fcc422b85e77e4c0468d9a44f885f5fa0be2",url="https://repo1.maven.org/maven2/org/sonatype/sisu/inject/cglib/2.2.1-v20090111/cglib-2.2.1-v20090111.jar",)http_jar(name="javax_inject_javax_inject",sha256="91c77044a50c481636c32d916fd89c9118a72195390452c81065080f957de7ff",url="https://repo1.maven.org/maven2/javax/inject/javax.inject/1/javax.inject-1.jar",)"

[
  https://repo1.maven.org/maven2/com/google/inject/guice/4.0/guice-4.0.jar,
  https://repo1.maven.org/maven2/org/sonatype/sisu/inject/cglib/2.2.1-v20090111/cglib-2.2.1-v20090111.jar, 
  https://repo1.maven.org/maven2/javax/inject/javax.inject/1/javax.inject-1.jar
]

I've tried the following, but it only gives me the first occurrence of it, but I need them all. Thanks!

var arr = contents.split('url=').pop().split(',')

for(i in arr) {
    console.log(arr[i]);
}

CodePudding user response：

You can solve this by using a Regular Expression

const regEx = /(?:url=")([^,] )(?:",)/gm;

const string = 'load("@bazel_tools//tools/build_defs/repo:http.bzl","http_jar")definclude_java_deps():http_jar(name="com_google_inject_guice",sha256="b378ffc35e7f7125b3c5f3a461d4591ae1685e3c781392f0c854ed7b7581d6d2",url="https://repo1.maven.org/maven2/com/google/inject/guice/4.0/guice-4.0.jar",)http_jar(name="org_sonatype_sisu_inject_cglib",sha256="42e1dfb26becbf1a633f25b47e39fcc422b85e77e4c0468d9a44f885f5fa0be2",url="https://repo1.maven.org/maven2/org/sonatype/sisu/inject/cglib/2.2.1-v20090111/cglib-2.2.1-v20090111.jar",)http_jar(name="javax_inject_javax_inject",sha256="91c77044a50c481636c32d916fd89c9118a72195390452c81065080f957de7ff",url="https://repo1.maven.org/maven2/javax/inject/javax.inject/1/javax.inject-1.jar",)'

const matches = string.matchAll(regEx);

for (const match of matches) {
  console.log(match[1]);
}

Or with string methods

const string = 'load("@bazel_tools//tools/build_defs/repo:http.bzl","http_jar")definclude_java_deps():http_jar(name="com_google_inject_guice",sha256="b378ffc35e7f7125b3c5f3a461d4591ae1685e3c781392f0c854ed7b7581d6d2",url="https://repo1.maven.org/maven2/com/google/inject/guice/4.0/guice-4.0.jar",)http_jar(name="org_sonatype_sisu_inject_cglib",sha256="42e1dfb26becbf1a633f25b47e39fcc422b85e77e4c0468d9a44f885f5fa0be2",url="https://repo1.maven.org/maven2/org/sonatype/sisu/inject/cglib/2.2.1-v20090111/cglib-2.2.1-v20090111.jar",)http_jar(name="javax_inject_javax_inject",sha256="91c77044a50c481636c32d916fd89c9118a72195390452c81065080f957de7ff",url="https://repo1.maven.org/maven2/javax/inject/javax.inject/1/javax.inject-1.jar",)'

const arr = string.split('url="');
const urls = arr
    .filter((subStr) => subStr.includes('https://'))
    .map((subStr) => subStr.split('",)')[0]);
console.log(urls);

The RegEx solution is of course widely more flexible.

Be aware that Regular Expressions can be "unsafe" which means they might have extremely long evaluation times depending on the input. Libraries like this can help you detect these