nixguix/test: Add all supported tarball extensions to test manifest

Next step is to add some extensions filtering so might as well harden the test dataset
first.

Related to T3781

swh/lister/nixguix/tests/data/sources-success.json

@@ -7,7 +7,7 @@
     },
     {
       "type": "url",
-      "urls": [ "https://github.com/owner-3/repository-1/revision-1.tgz" ],
+      "urls": [ "https://github.com/owner-3/repository-1/revision-1.tar" ],
       "integrity": "sha256-3vm2Nt+O4zHf3Ovd/qsv1gKTEUwodX9FLxlrQdry0zs="
     },
     {
@@ -52,7 +52,7 @@
       "outputHashMode": "recursive",
       "type": "url",
       "urls": [
-        "https://github.com/kandu/trie/archive/1.0.0.tar.gz"
+        "https://github.com/kandu/trie/archive/1.0.0.txz"
       ],
       "integrity": "sha256-j7xp1svMeYIm+WScVe/B7w0jNjMtvkp9a1hLLLlO92g=",
       "inferredFetcher": "fetchzip"
@@ -85,7 +85,7 @@
       "outputHashMode": "recursive",
       "type": "url",
       "urls": [
-        "https://github.com/julian-klode/triehash/archive/debian/0.3-3.tar.gz"
+        "https://github.com/julian-klode/triehash/archive/debian/0.3-3.tbz"
       ],
       "inferredFetcher": "fetchzip"
     },
@@ -177,6 +177,94 @@
       ],
       "integrity": "sha256-VQYMZNYqNBZ9+01YCcabqqIfck/mU/BRcFZKXpBEX00=",
       "inferredFetcher": "unclassified"
+    },
+    {
+      "type": "url",
+      "urls": [
+        "https://crates.io/api/v1/crates/syntect/4.6.0/download"
+      ],
+      "integrity": "sha256-iyCBW76A7gvgbmlXRQqEEYX89pD+AXjxTXegXOLKoDE="
+    },
+    {
+      "outputHash": "0x5l2pn4x92734k6i2wcjbn2klmwgkiqaajvxadh35k74dgnyh18",
+      "outputHashAlgo": "sha256",
+      "outputHashMode": "flat",
+      "type": "url",
+      "urls": [
+        "https://rubygems.org/gems/wdm-0.1.1.gem"
+      ],
+      "integrity": "sha256-KEBvXyNnlgGb6lsqheN8vNIp7JKMi2gmGUekTuwVtHQ=",
+      "inferredFetcher": "unclassified"
+    },
+    {
+      "outputHash": "2al10188nwrdmi9zk3bid4ijjfsa8ymh6m9hin5jsja7hx7anbvs3i2y7kall56h4qn7j1rj73f8499x3i2k6x53kszmksvd2a1pkd4",
+      "outputHashAlgo": "sha512",
+      "outputHashMode": "flat",
+      "type": "url",
+      "urls": [
+        "https://repo1.maven.org/maven2/org/codehaus/plexus/plexus-compiler-manager/2.4/plexus-compiler-manager-2.4.jar"
+      ],
+      "integrity": "sha512-pM0blGhbz/r1HKWbKeLoKRHkxpE5yGMxgaZQqubxIg69l1Wnw6OklsVGmKqB1SOlnZSRtLjG/CnWlrlFKIBAlQ==",
+      "inferredFetcher": "unclassified"
+    },
+    {
+      "outputHash": "19mnq9a1yr16srqs8n6hddahr4f9d2gbpmld62pvlw1ps7nfrp9w",
+      "outputHashAlgo": "sha256",
+      "outputHashMode": "recursive",
+      "type": "url",
+      "urls": [
+        "https://bitbucket.org/zandoye/charinfo_width/get/1.1.0.tar.bz2"
+      ],
+      "integrity": "sha256-PN3s7NE3cLqvMI3Wu55oyZEMVWvQWKRx1iZkH1TCtqY=",
+      "inferredFetcher": "fetchzip"
+    },
+    {
+      "type": "url",
+      "urls": [
+        "https://ftpmirror.gnu.org/gnu/texinfo/texinfo-4.13a.tar.lzma",
+        "ftp://ftp.cs.tu-berlin.de/pub/gnu/texinfo/texinfo-4.13a.tar.lzma"
+      ],
+      "integrity": "sha256-bSiwzq6GbjU2FC/FUuejvJ+EyDAxGcJXMbJHju9kyeU="
+    },
+    {
+      "type": "url",
+      "urls": [
+        "https://download.savannah.gnu.org/releases/zutils/zutils-1.10.tar.lz",
+        "https://nongnu.freemirror.org/nongnu/zutils/zutils-1.10.tar.lz"
+      ],
+      "integrity": "sha256-DdRBOCktV1dkgDcZW2lFw99wsxYiG0KFUgrTjy6usZU="
+    },
+    {
+      "type": "url",
+      "urls": [
+        "http://www.rle.mit.edu/cpg/codes/fasthenry-3.0-12Nov96.tar.z"
+      ],
+      "integrity": "sha256-8V9YKMP4A50xYvmFlzh5sbQv6L39hD+znfAD0rzvBqg="
+    },
+    {
+      "type": "url",
+      "urls": [
+        "http://ftp.x.org/contrib/utilities/unclutter-8.tar.Z"
+      ],
+      "integrity": "sha256-uFWnjURlqy+GKH6srGOnPxUEsIUihAqjdxh3bn7JGSo="
+    },
+    {
+      "outputHash": "sha256-Y40oLjddunrd7ZF1JbCcgjSCn8jFTubq69jhAVxInXw=",
+      "outputHashAlgo": "sha256",
+      "outputHashMode": "flat",
+      "type": "url",
+      "urls": [
+        "https://github.com/vk-cli/vk/releases/download/0.7.6/vk-0.7.6-64-bin.7z"
+      ],
+      "integrity": "sha256-Y40oLjddunrd7ZF1JbCcgjSCn8jFTubq69jhAVxInXw=",
+      "inferredFetcher": "unclassified"
+    },
+    {
+      "type": "url",
+      "urls": [
+        "https://github.com/Doom-Utils/deutex/releases/download/v5.2.2/deutex-5.2.2.tar.zst"
+      ],
+      "integrity": "sha256-EO0OelM+yXy20DVI1CWPvsiIUqRbXqTPVDQ3atQXS18="
     }
   ],
   "version": "1",

swh/lister/nixguix/tests/test_lister.py

@@ -188,6 +188,12 @@ def test_lister_nixguix_ok(datadir, swh_scheduler, requests_mock):
         "http://git.marmaro.de/?p=mmh;a=snapshot;h=431604647f89d5aac7b199a7883e98e56e4ccf9e;sf=tgz",
         headers={"Content-Type": "application/gzip; charset=ISO-8859-1"},
     )
+    requests_mock.head(
+        "https://crates.io/api/v1/crates/syntect/4.6.0/download",
+        headers={
+            "Location": "https://static.crates.io/crates/syntect/syntect-4.6.0.crate"
+        },
+    )
 
     expected_visit_types = defaultdict(int)
     # origin upstream is added as origin
@@ -211,6 +217,8 @@ def test_lister_nixguix_ok(datadir, swh_scheduler, requests_mock):
                 expected_visit_types["content"] += 1
             elif url.startswith("svn"):  # mistyped artifact rendered as vcs nonetheless
                 expected_visit_types["svn"] += 1
+            elif "crates.io" in url:
+                expected_visit_types["directory"] += 1
             else:  # tarball artifacts
                 expected_visit_types["directory"] += 1