From 75ab064d2b38e70746af1718ed7cdbafb906249e Mon Sep 17 00:00:00 2001
From: Yousong Zhou <yszhou4tech@gmail.com>
Date: Sun, 11 Feb 2018 17:42:22 +0800
Subject: build: download code from github using archive API

A new python script scripts/download.py is added to fetch tarballs using
GitHub archive API [1], then repack in a reproducible way same as the
current DownloadMethod/git

GitHub imposes a 60 reqs/hour rate limit on unauthenticated API
access[2].  This affects fetching commit date for feeding tar --mtime=
argument.  However, observation indicates that archive download is NOT
subject to this limit at the moment.  In the rare cases where download
fails because of this, we will falback to using DownloadMethod/git

The missing piece in the GitHub API is that it cannot provide in the
tarball dependent submodules's source code.  In that case, the
implementation will also fallback to using DownloadMethod/git

 [1] Get archive link, https://developer.github.com/v3/repos/contents/#get-archive-link
 [2] Rate limiting, https://developer.github.com/v3/#rate-limiting

v2 <- v1:

 - allow passing multiple urls with --urls argument
 - add commit ts cache.  can be helpful on retry

Signed-off-by: Yousong Zhou <yszhou4tech@gmail.com>
---
 include/download.mk | 74 +++++++++++++++++++++++++++++++----------------------
 1 file changed, 43 insertions(+), 31 deletions(-)

(limited to 'include')

diff --git a/include/download.mk b/include/download.mk
index 2ba8a7bdf4..91a22c2316 100644
--- a/include/download.mk
+++ b/include/download.mk
@@ -21,23 +21,7 @@ DOWNLOAD_RDEP=$(STAMP_PREPARED) $(HOST_STAMP_PREPARED)
 
 # Try to guess the download method from the URL
 define dl_method
-$(strip \
-  $(if $(2),$(2), \
-    $(if $(filter @APACHE/% @GITHUB/% @GNOME/% @GNU/% @KERNEL/% @SF/% @SAVANNAH/% ftp://% http://% https://% file://%,$(1)),default, \
-      $(if $(filter git://%,$(1)),git, \
-        $(if $(filter svn://%,$(1)),svn, \
-          $(if $(filter cvs://%,$(1)),cvs, \
-            $(if $(filter hg://%,$(1)),hg, \
-              $(if $(filter sftp://%,$(1)),bzr, \
-                unknown \
-              ) \
-            ) \
-          ) \
-        ) \
-      ) \
-    ) \
-  ) \
-)
+$(shell $(SCRIPT_DIR)/download.py dl_method --url $(foreach url,$(1),"$(url)") --proto="$(2)")
 endef
 
 # code for creating tarballs from cvs/svn/git/bzr/hg/darcs checkouts - useful for mirror support
@@ -56,6 +40,10 @@ ifdef CHECK
 check_escape=$(subst ','\'',$(1))
 #')
 
+# $(1): suffix of the F_, C_ variables, e.g. hash_deprecated, hash_mismatch, etc.
+# $(2): filename
+# $(3): expected hash value
+# $(4): hash var name: MD5SUM, HASH
 check_warn_nofix = $(info $(shell printf "$(_R)WARNING: %s$(_N)" '$(call check_escape,$(call C_$(1),$(2),$(3),$(4)))'))
 ifndef FIXUP
   check_warn = $(check_warn_nofix)
@@ -71,6 +59,9 @@ F_hash_mismatch = $(F_hash_deprecated)
 F_hash_missing = $(SCRIPT_DIR)/fixup-makefile.pl $(CURDIR)/Makefile add-hash $(3) $(call gen_sha256sum,$(1))
 endif
 
+# $(1): filename
+# $(2): expected hash value
+# $(3): hash var name: MD5SUM, HASH
 C_download_missing = $(1) is missing, please run make download before re-running this check
 C_hash_mismatch = $(3) does not match $(1) hash $(call gen_sha256sum,$(1))
 C_hash_deprecated = $(3) uses deprecated hash, set to $(call gen_sha256sum,$(1))
@@ -116,6 +107,9 @@ define DownloadMethod/default
 	)
 endef
 
+# $(1): "check"
+# $(2): "PKG_" if <name> as in Download/<name> is "default", otherwise "Download/<name>:"
+# $(3): shell command sequence to do the download
 define wrap_mirror
 $(if $(if $(MIRROR),$(filter-out x,$(MIRROR_HASH))),$(SCRIPT_DIR)/download.pl "$(DL_DIR)" "$(FILE)" "$(MIRROR_HASH)" "" || ( $(3) ),$(3)) \
 $(if $(filter check,$(1)), \
@@ -159,23 +153,41 @@ endef
 
 define DownloadMethod/git
 	$(call wrap_mirror,$(1),$(2), \
-		echo "Checking out files from the git repository..."; \
-		mkdir -p $(TMP_DIR)/dl && \
-		cd $(TMP_DIR)/dl && \
-		rm -rf $(SUBDIR) && \
-		[ \! -d $(SUBDIR) ] && \
-		git clone $(OPTS) $(URL) $(SUBDIR) && \
-		(cd $(SUBDIR) && git checkout $(VERSION) && \
-		git submodule update --init --recursive) && \
-		echo "Packing checkout..." && \
-		export TAR_TIMESTAMP=`cd $(SUBDIR) && git log -1 --format='@%ct'` && \
-		rm -rf $(SUBDIR)/.git && \
-		$(call dl_tar_pack,$(TMP_DIR)/dl/$(FILE),$(SUBDIR)) && \
-		mv $(TMP_DIR)/dl/$(FILE) $(DL_DIR)/ && \
-		rm -rf $(SUBDIR); \
+		$(call DownloadMethod/git-raw) \
 	)
 endef
 
+define DownloadMethod/github-tarball
+	$(call wrap_mirror,$(1),$(2), \
+		$(SCRIPT_DIR)/download.py dl \
+			--dl-dir="$(DL_DIR)" \
+			--url $(foreach url,$(URL),"$(url)") \
+			--proto="$(PROTO)" \
+			--version="$(VERSION)" \
+			--subdir="$(SUBDIR)" \
+			--source="$(FILE)" \
+		|| ( $(call DownloadMethod/git-raw) ); \
+	)
+endef
+
+# Only intends to be called as a submethod from other DownloadMethod
+define DownloadMethod/git-raw
+	echo "Checking out files from the git repository..."; \
+	mkdir -p $(TMP_DIR)/dl && \
+	cd $(TMP_DIR)/dl && \
+	rm -rf $(SUBDIR) && \
+	[ \! -d $(SUBDIR) ] && \
+	git clone $(OPTS) $(URL) $(SUBDIR) && \
+	(cd $(SUBDIR) && git checkout $(VERSION) && \
+	git submodule update --init --recursive) && \
+	echo "Packing checkout..." && \
+	export TAR_TIMESTAMP=`cd $(SUBDIR) && git log -1 --format='@%ct'` && \
+	rm -rf $(SUBDIR)/.git && \
+	$(call dl_tar_pack,$(TMP_DIR)/dl/$(FILE),$(SUBDIR)) && \
+	mv $(TMP_DIR)/dl/$(FILE) $(DL_DIR)/ && \
+	rm -rf $(SUBDIR);
+endef
+
 define DownloadMethod/bzr
 	$(call wrap_mirror,$(1),$(2), \
 		echo "Checking out files from the bzr repository..."; \
-- 
cgit v1.2.3