Implement #624: Use shorter hashes with CPM_SOURCE_CACHE (#631)

* Add ASSERT_CONTENTS_EQUAL test macro in testing.cmake

Checks if the contents of a file matches the given input

* Use shorter hashes with CPM_SOURCE_CACHE (#624)

Uses shorter hashes with CPM_SOURCE_CACHE. Falls back to a longer hash
if necessary (ie, if there's a collision with an existing hash).

See: https://github.com/cpm-cmake/CPM.cmake/issues/624

* Update integration tests to support shorter hashes

* trigger ci

* run cmake-format

* if already available, use the legacy cache hash

* create temporary file in current binary dir

* add test case for legacy hash

---------

Co-authored-by: Lars Melchior <lars.melchior@gmail.com>
Co-authored-by: Lars Melchior <TheLartians@users.noreply.github.com>

cmake/CPM.cmake

@@ -202,6 +202,60 @@ function(cpm_package_name_from_git_uri URI RESULT)
   endif()
 endfunction()
 
+# Find the shortest hash that can be used eg, if origin_hash is
+# cccb77ae9609d2768ed80dd42cec54f77b1f1455 the following files will be checked, until one is found
+# that is either empty (allowing us to assign origin_hash), or whose contents matches ${origin_hash}
+#
+# * .../cccb.hash
+# * .../cccb77ae.hash
+# * .../cccb77ae9609.hash
+# * .../cccb77ae9609d276.hash
+# * etc
+#
+# We will be able to use a shorter path with very high probability, but in the (rare) event that the
+# first couple characters collide, we will check longer and longer substrings.
+function(cpm_get_shortest_hash source_cache_dir origin_hash short_hash_output_var)
+  # for compatibility with caches populated by a previous version of CPM, check if a directory using
+  # the full hash already exists
+  if(EXISTS "${source_cache_dir}/${origin_hash}")
+    set(${short_hash_output_var}
+        "${origin_hash}"
+        PARENT_SCOPE
+    )
+    return()
+  endif()
+
+  foreach(len RANGE 4 40 4)
+    string(SUBSTRING "${origin_hash}" 0 ${len} short_hash)
+    set(hash_lock ${source_cache_dir}/${short_hash}.lock)
+    set(hash_fp ${source_cache_dir}/${short_hash}.hash)
+    # Take a lock, so we don't have a race condition with another instance of cmake. We will release
+    # this lock when we can, however, if there is an error, we want to ensure it gets released on
+    # it's own on exit from the function.
+    file(LOCK ${hash_lock} GUARD FUNCTION)
+
+    # Load the contents of .../${short_hash}.hash
+    file(TOUCH ${hash_fp})
+    file(READ ${hash_fp} hash_fp_contents)
+
+    if(hash_fp_contents STREQUAL "")
+      # Write the origin hash
+      file(WRITE ${hash_fp} ${origin_hash})
+      file(LOCK ${hash_lock} RELEASE)
+      break()
+    elseif(hash_fp_contents STREQUAL origin_hash)
+      file(LOCK ${hash_lock} RELEASE)
+      break()
+    else()
+      file(LOCK ${hash_lock} RELEASE)
+    endif()
+  endforeach()
+  set(${short_hash_output_var}
+      "${short_hash}"
+      PARENT_SCOPE
+  )
+endfunction()
+
 # Try to infer package name and version from a url
 function(cpm_package_name_and_ver_from_url url outName outVer)
   if(url MATCHES "[/\\?]([a-zA-Z0-9_\\.-]+)\\.(tar|tar\\.gz|tar\\.bz2|zip|ZIP)(\\?|/|$)")
@@ -806,9 +860,19 @@ function(CPMAddPackage)
       set(download_directory ${CPM_SOURCE_CACHE}/${lower_case_name}/${CPM_ARGS_CUSTOM_CACHE_KEY})
     elseif(CPM_USE_NAMED_CACHE_DIRECTORIES)
       string(SHA1 origin_hash "${origin_parameters};NEW_CACHE_STRUCTURE_TAG")
+      cpm_get_shortest_hash(
+        "${CPM_SOURCE_CACHE}/${lower_case_name}" # source cache directory
+        "${origin_hash}" # Input hash
+        origin_hash # Computed hash
+      )
       set(download_directory ${CPM_SOURCE_CACHE}/${lower_case_name}/${origin_hash}/${CPM_ARGS_NAME})
     else()
       string(SHA1 origin_hash "${origin_parameters}")
+      cpm_get_shortest_hash(
+        "${CPM_SOURCE_CACHE}/${lower_case_name}" # source cache directory
+        "${origin_hash}" # Input hash
+        origin_hash # Computed hash
+      )
       set(download_directory ${CPM_SOURCE_CACHE}/${lower_case_name}/${origin_hash})
     endif()
     # Expand `download_directory` relative path. This is important because EXISTS doesn't work for

cmake/testing.cmake

@@ -79,3 +79,16 @@ function(ASSERT_NOT_EXISTS file)
     message(FATAL_ERROR "assertion failed: file ${file} exists")
   endif()
 endfunction()
+
+function(ASSERT_CONTENTS_EQUAL file content)
+  if(EXISTS ${file})
+    file(READ ${file} file_content)
+    if(content STREQUAL file_content)
+      message(STATUS "test passed: '${file}' exists and contains '${content}'")
+    else()
+      message(FATAL_ERROR "assertion failed: file '${file}' does not contain expected content.")
+    endif()
+  else()
+    message(FATAL_ERROR "assertion failed: file '${file} does not exist")
+  endif()
+endfunction()