Make the get_sources shell script support flat layout

The idea of this commit is to make get_sources.sh support both the
'traditional' git layout used on dist-git for CentOS Linux where the
spec files are stored in a SPECS folder and the patches in a SOURCES
folder with the sha of the tarball being in a '.<pkg_name>.metadata'
file as well as the 'flat' git layout that have adopted Fedora as well
as CentOS-Stream (9+) where the spec files and patches are all stored
at the top level directory of the repository and the sha of the tarball
is present in a 'sources' file.

This commit re-uses code from the fedpkg-minimal project which is
license under the GPL (so the License field of the spec file for
centpkg-minimal may need to be adjusted to MIT and GPL).

Signed-off-by: Pierre-Yves Chibon <pingou@pingoured.fr>

get_sources.sh

@@ -9,6 +9,7 @@
 #                  Pat Riehecky <riehecky@fnal.gov>
 #                  Tyler Parsons <tparsons@fnal.gov>
 #                  Tuomo Soini <tis@foobar.fi>
+set -eux
 
 
 #####################################################################
@@ -114,10 +115,83 @@ if [[ $? -ne 0 ]]; then
     exit 1
 fi
 
+if [ ! -d .git ] && ([ ! -d SPECS ] || [[ ! -s sources ]] ); then
+      echo 'You need to run this from inside a sources git repo' >&2
+      exit 1
+    fi
+
+# sort out our branch
+if [ -n "$BRANCH" ]
+then
+  branches=("$BRANCH")
+else
+  # generate a list of all branches containing current HEAD
+  branches=()
+  while IFS='' read -r line
+  do
+    # input from: git branch --contains HEAD
+    branch="${line:2}"
+    if [[ "$branch" =~ "detached from" ]]
+    then
+      # ignore detached heads
+      continue
+    fi
+    if [ ".${line:0:1}" = ".*" ]
+    then
+      # current branch, put it first
+      branches=("$branch" "${branches[@]}")
+    else
+      branches=("${branches[@]}" "$branch")
+    fi
+  done <<< "$(git branch -r --contains HEAD | sed 's#origin/##g')"
+fi
+
+if [[ -s sources ]]; then
+    # This section is for the "flat" dist-git layout, where the spec file and
+    # patches are all present at the top level directory and the sha of the tarball
+    # present in a 'sources' file.
+    # This code was re-used from the fedpkg-pkg minimal project which is licensed
+    # under GPLv3 or any later version.
+
+    pkgname=$(basename "$PWD")
+    # Read first word of first line. For old MD5 format it's the 32 character
+    # hash. Otherwise let's assume the sources have the BSD format where lines
+    # start with hash type.
+    hashtype="$(head -n1 sources | cut -d' ' -f1 | tr '[:upper:]' '[:lower:]')"
+    # The format is
+    #   SHA512 (filename) = ABCDEF
+    # We don't care about the equals sign. We also assume all hashes are
+    # the same type, so we don't need to read it again for each line.
+    while read -r _ filename _ hash || [[ -n "$filename" && -n "$hash" ]]; do
+        if [ -z "$filename" ] || [ -z "$hash" ]; then
+            continue
+        fi
+        # Remove parenthesis around tarball name
+        filename=${filename#(}
+        tarball=${filename%)}
+        if [ ! -e "$tarball" ]; then
+          for br in "${branches[@]}"
+          do
+            br=$(echo ${br}| sed -e s'|remotes/origin/||')
+            url="${SURL}/$pkgname/${br}/$hash"
+            echo "Retrieving ${url}"
+            curl -L ${QUIET} -f "${url}" -o "$tarball" && break
+          done
+        else
+          echo "$filename exists. skipping"
+        fi
+    done < sources
+    "${hashtype}sum" -c sources
+else
+    # This section is for the "non-flat" dist-git layout, where the spec file
+    # is stored in a SPECS folder, the patches in a SOURCES folder and the sha
+    # of the tarball of the project is present in a '.<pkg_name>.metadata' file.
+
+    mkdir -p SOURCES
     # should go into a function section at some point
     weakHashDetection () {
       strHash=${1};
-  case $((`echo "${strHash}"|wc -m` - 1 )) in
+      case $((`echo ${strHash}|wc -m` - 1 )) in
         128)
           hashBin='sha512sum'
           ;;
@@ -152,49 +226,18 @@ meta=$1
     pn=${meta%.metadata}
     pn=${pn#.}
 
-if [ ! -d .git ] || [ ! -d SPECS ]; then
-  echo 'You need to run this from inside a sources git repo' >&2
-  exit 1
-fi
-mkdir -p SOURCES
-
-# sort out our branch
-if [ -n "$BRANCH" ]
-then
-  branches=("$BRANCH")
-else
-  # generate a list of all branches containing current HEAD
-  branches=()
-  while IFS='' read -r line
-  do
-    # input from: git branch --contains HEAD
-    branch="${line:2}"
-    if [[ "$branch" =~ "detached from" ]]
-    then
-      # ignore detached heads
-      continue
-    fi
-    if [ ".${line:0:1}" = ".*" ]
-    then
-      # current branch, put it first
-      branches=("$branch" "${branches[@]}")
-    else
-      branches=("${branches[@]}" "$branch")
-    fi
-  done <<< "$(git branch -r --contains HEAD | grep '^\s\+origin/'| sed 's#origin/##g')"
-fi
     while read -r fsha fname ; do
       if [ ".${fsha}" = ".da39a3ee5e6b4b0d3255bfef95601890afd80709" ]; then
         # zero byte file
-    touch "${fname}"
+        touch ${fname}
       else
         if [ ${CHECK} -eq 1 ]; then
-      hashType=$(weakHashDetection "${fsha}")
+          hashType=$(weakHashDetection ${fsha})
           if [ "${hashType}" == "unknown" ]; then
             echo 'Failure: Hash type unknown.' >&2
             exit 1;
           else
-        command -v "${hashType}" >/dev/null 2>&1
+            which ${hashType} >/dev/null 2>&1
             if [[ $? -ne 0 ]]; then
               echo "Failure: You need ${hashType} in PATH." >&2
               exit 1;
@@ -203,15 +246,15 @@ while read -r fsha fname ; do
         fi
         if [ -e ${fname} -a ${CHECK} -eq 1 ]; then
 	    # check hash sum and force download if wrong
-        downsum=$(${hashType} "${fname}" | awk '{print $1}')
+            downsum=$(${hashType} ${fname} | awk '{print $1}')
             if [ "${fsha}" != "${downsum}" ]; then
-            rm -f "${fname}"
+                rm -f ${fname}
             fi
         fi
         if [ ! -e "${fname}" ]; then
           for br in "${branches[@]}"
           do
-        br=$(echo "${br}"| sed -e s'|remotes/origin/||')
+            br=$(echo ${br}| sed -e s'|remotes/origin/||')
             url="${SURL}/${pn}/${br}/${fsha}"
             echo "Retrieving ${url}"
             curl -L ${QUIET} -f "${url}" -o "${fname}" && break
@@ -220,12 +263,14 @@ while read -r fsha fname ; do
           echo "${fname} exists. skipping"
         fi
         if [ ${CHECK} -eq 1 ]; then
-        downsum=$(${hashType} "${fname}" | awk '{print $1}')
+            downsum=$(${hashType} ${fname} | awk '{print $1}')
             if [ "${fsha}" != "${downsum}" ]; then
-            rm -f "${fname}"
+                rm -f ${fname}
                 echo "Failure: ${fname} hash does not match hash from the .metadata file" >&2
                 exit 1;
             fi
         fi
       fi
     done < "${meta}"
+
+fi