import: pypi: Support more types of archives.

This change enables the PyPI importer to look for requirements in a source
archive of a different type than "tar.gz" or "tar.bz2".  Also, scan the source
archive to find a requires.txt file.

* guix/import/pypi.scm: (guess-requirements)[tarball-directory]: Remove procedure.
[guess-requirements-from-source]: Use COMRESSED-FILE? to determine if an
archive type is supported, and some file extension logic that chooses either
"tar" or "unzip" as the extractor.  Search for the requires.txt file in the
archive instead of using a static, expected location.
(guess-requirements): Rename the TARBALL argument to ARCHIVE, to denote the
archive format is no longer bound specifically to the Tar format.
(compute-inputs): Likewise.
* tests/pypi.scm ("pypi->guix-package, no wheel"): Mock the requires.txt at a
non-standard location.
("pypi->guix-package, no usable requirement file."): New test.

2 files changed, 83 insertions, 46 deletions

diff --git a/guix/import/pypi.scm b/guix/import/pypi.scm
index ad59a8b731..a6106ab4ec 100644
--- a/guix/import/pypi.scm
+++ b/guix/import/pypi.scm
@@ -39,7 +39,8 @@
   #:use-module ((guix build utils)
                 #:select ((package-name->name+version
                            . hyphen-package-name->name+version)
-                          find-files))
+                          find-files
+                          invoke))
   #:use-module (guix import utils)
   #:use-module ((guix download) #:prefix download:)
   #:use-module (guix import json)
@@ -189,28 +190,11 @@ requirement names."
                 (loop (cons (specification->requirement-name line)
                             result))))))))))
 
-(define (guess-requirements source-url wheel-url tarball)
-  "Given SOURCE-URL, WHEEL-URL and a TARBALL of the package, return a list
-of the required packages specified in the requirements.txt file.  TARBALL will
+(define (guess-requirements source-url wheel-url archive)
+  "Given SOURCE-URL, WHEEL-URL and a ARCHIVE of the package, return a list
+of the required packages specified in the requirements.txt file.  ARCHIVE will
 be extracted in a temporary directory."
 
-  (define (tarball-directory url)
-    ;; Given the URL of the package's tarball, return the name of the directory
-    ;; that will be created upon decompressing it. If the filetype is not
-    ;; supported, return #f.
-    ;; TODO: Support more archive formats.
-    (let ((basename (substring url (+ 1 (string-rindex url #\/)))))
-      (cond
-       ((string-suffix? ".tar.gz" basename)
-        (string-drop-right basename 7))
-       ((string-suffix? ".tar.bz2" basename)
-        (string-drop-right basename 8))
-       (else
-        (begin
-          (warning (G_ "Unsupported archive format: \
-cannot determine package dependencies"))
-          #f)))))
-
   (define (read-wheel-metadata wheel-archive)
     ;; Given WHEEL-ARCHIVE, a ZIP Python wheel archive, return the package's
     ;; requirements.
@@ -239,29 +223,34 @@ cannot determine package dependencies"))
     (call-with-temporary-output-file
      (lambda (temp port)
        (if wheel-url
-         (and (url-fetch wheel-url temp)
-              (read-wheel-metadata temp))
-         #f))))
+           (and (url-fetch wheel-url temp)
+                (read-wheel-metadata temp))
+           #f))))
 
   (define (guess-requirements-from-source)
     ;; Return the package's requirements by guessing them from the source.
-    (let ((dirname (tarball-directory source-url)))
-      (if (string? dirname)
-          (call-with-temporary-directory
-           (lambda (dir)
-             (let* ((pypi-name (string-take dirname (string-rindex dirname #\-)))
-                    (requires.txt (string-append dirname "/" pypi-name
-                                                 ".egg-info" "/requires.txt"))
-                    (exit-code (parameterize ((current-error-port (%make-void-port "rw+"))
-                                              (current-output-port (%make-void-port "rw+")))
-                                 (system* "tar" "xf" tarball "-C" dir requires.txt))))
-               (if (zero? exit-code)
-                   (parse-requires.txt (string-append dir "/" requires.txt))
-                   (begin
-                     (warning
-                      (G_ "Failed to extract file: ~a from source.~%")
-                      requires.txt)
-                     '())))))
+    (if (compressed-file? source-url)
+        (call-with-temporary-directory
+         (lambda (dir)
+           (parameterize ((current-error-port (%make-void-port "rw+"))
+                          (current-output-port (%make-void-port "rw+")))
+             (if (string=? "zip" (file-extension source-url))
+                 (invoke "unzip" archive "-d" dir)
+                 (invoke "tar" "xf" archive "-C" dir)))
+           (let ((requires.txt-files
+                  (find-files dir (lambda (abs-file-name _)
+		                    (string-match "\\.egg-info/requires.txt$"
+                                                  abs-file-name)))))
+             (match requires.txt-files
+               (()
+                (warning (G_ "Cannot guess requirements from source archive:\
+ no requires.txt file found.~%"))
+                '())
+               (else (parse-requires.txt (first requires.txt-files)))))))
+        (begin
+          (warning (G_ "Unsupported archive format; \
+cannot determine package dependencies from source archive: ~a~%")
+                   (basename source-url))
           '())))
 
   ;; First, try to compute the requirements using the wheel, else, fallback to
@@ -270,13 +259,13 @@ cannot determine package dependencies"))
   (or (guess-requirements-from-wheel)
       (guess-requirements-from-source)))
 
-(define (compute-inputs source-url wheel-url tarball)
-  "Given the SOURCE-URL of an already downloaded TARBALL, return a list of
+(define (compute-inputs source-url wheel-url archive)
+  "Given the SOURCE-URL of an already downloaded ARCHIVE, return a list of
 name/variable pairs describing the required inputs of this package.  Also
 return the unaltered list of upstream dependency names."
   (let ((dependencies
          (remove (cut string=? "argparse" <>)
-                 (guess-requirements source-url wheel-url tarball))))
+                 (guess-requirements source-url wheel-url archive))))
     (values (sort
              (map (lambda (input)
                     (let ((guix-name (python->package-name input)))
diff --git a/tests/pypi.scm b/tests/pypi.scm
index c40be6c21d..b45d2c9d2f 100644
--- a/tests/pypi.scm
+++ b/tests/pypi.scm
@@ -20,6 +20,7 @@
 (define-module (test-pypi)
   #:use-module (guix import pypi)
   #:use-module (guix base32)
+  #:use-module (guix memoization)
   #:use-module (gcrypt hash)
   #:use-module (guix tests)
   #:use-module (guix build-system python)
@@ -134,8 +135,9 @@ pytest (>=2.5.0)
              (match url
                ("https://example.com/foo-1.0.0.tar.gz"
                 (begin
-                  (mkdir-p "foo-1.0.0/foo.egg-info/")
-                  (with-output-to-file "foo-1.0.0/foo.egg-info/requires.txt"
+                  ;; Unusual requires.txt location should still be found.
+                  (mkdir-p "foo-1.0.0/src/bizarre.egg-info")
+                  (with-output-to-file "foo-1.0.0/src/bizarre.egg-info/requires.txt"
                     (lambda ()
                       (display test-requires.txt)))
                   (parameterize ((current-output-port (%make-void-port "rw+")))
@@ -241,4 +243,50 @@ pytest (>=2.5.0)
                 (x
                  (pk 'fail x #f))))))
 
+(test-assert "pypi->guix-package, no usable requirement file."
+  ;; Replace network resources with sample data.
+  (mock ((guix import utils) url-fetch
+         (lambda (url file-name)
+           (match url
+             ("https://example.com/foo-1.0.0.tar.gz"
+              (mkdir-p "foo-1.0.0/foo.egg-info/")
+              (parameterize ((current-output-port (%make-void-port "rw+")))
+                (system* "tar" "czvf" file-name "foo-1.0.0/"))
+              (delete-file-recursively "foo-1.0.0")
+              (set! test-source-hash
+                (call-with-input-file file-name port-sha256)))
+             ("https://example.com/foo-1.0.0-py2.py3-none-any.whl" #f)
+             (_ (error "Unexpected URL: " url)))))
+        (mock ((guix http-client) http-fetch
+               (lambda (url . rest)
+                 (match url
+                   ("https://pypi.org/pypi/foo/json"
+                    (values (open-input-string test-json)
+                            (string-length test-json)))
+                   ("https://example.com/foo-1.0.0-py2.py3-none-any.whl" #f)
+                   (_ (error "Unexpected URL: " url)))))
+              ;; Not clearing the memoization cache here would mean returning the value
+              ;; computed in the previous test.
+              (invalidate-memoization! pypi->guix-package)
+              (match (pypi->guix-package "foo")
+                (('package
+                   ('name "python-foo")
+                   ('version "1.0.0")
+                   ('source ('origin
+                              ('method 'url-fetch)
+                              ('uri ('pypi-uri "foo" 'version))
+                              ('sha256
+                               ('base32
+                                (? string? hash)))))
+                   ('build-system 'python-build-system)
+                   ('home-page "http://example.com")
+                   ('synopsis "summary")
+                   ('description "summary")
+                   ('license 'license:lgpl2.0))
+                 (string=? (bytevector->nix-base32-string
+                            test-source-hash)
+                           hash))
+                (x
+                 (pk 'fail x #f))))))
+
 (test-end "pypi")