[GitHub] [arrow] kou commented on a change in pull request #9367: ARROW-7288: [C++][Parquet] Don't use regular expression to parse application version

[GitBox <gi...@apache.org>]

kou commented on a change in pull request #9367:
URL: https://github.com/apache/arrow/pull/9367#discussion_r567323043



##########
File path: cpp/src/parquet/metadata.cc
##########
@@ -949,43 +910,278 @@ ApplicationVersion::ApplicationVersion(std::string application, int major, int m
                                        int patch)
     : application_(std::move(application)), version{major, minor, patch, "", "", ""} {}
 
-ApplicationVersion::ApplicationVersion(const std::string& created_by) {
-  // Use singletons to compile only once (ARROW-9863)
-  static regex app_regex{ApplicationVersion::APPLICATION_FORMAT};
-  static regex ver_regex{ApplicationVersion::VERSION_FORMAT};
-  smatch app_matches;
-  smatch ver_matches;
-
-  std::string created_by_lower = created_by;
-  std::transform(created_by_lower.begin(), created_by_lower.end(),
-                 created_by_lower.begin(), ::tolower);
-
-  bool app_success = regex_match(created_by_lower, app_matches, app_regex);
-  bool ver_success = false;
-  std::string version_str;
-
-  if (app_success && app_matches.size() >= 4) {
-    // first match is the entire string. sub-matches start from second.
-    application_ = app_matches[1];
-    version_str = app_matches[3];
-    build_ = app_matches[4];
-    ver_success = regex_match(version_str, ver_matches, ver_regex);
-  } else {
-    application_ = "unknown";
-  }
-
-  if (ver_success && ver_matches.size() >= 7) {
-    version.major = atoi(ver_matches[1].str().c_str());
-    version.minor = atoi(ver_matches[2].str().c_str());
-    version.patch = atoi(ver_matches[3].str().c_str());
-    version.unknown = ver_matches[4].str();
-    version.pre_release = ver_matches[5].str();
-    version.build_info = ver_matches[6].str();
-  } else {
-    version.major = 0;
-    version.minor = 0;
-    version.patch = 0;
+namespace {
+// Parse the application version format and set parsed values to
+// ApplicationVersion.
+//
+// The application version format:
+//   "${APPLICATION_NAME}"
+//   "${APPLICATION_NAME} version ${VERSION}"
+//   "${APPLICATION_NAME} version ${VERSION} (build ${BUILD_NAME})"
+//
+// Eg:
+//   parquet-cpp
+//   parquet-cpp version 1.5.0ab-xyz5.5.0+cd
+//   parquet-cpp version 1.5.0ab-xyz5.5.0+cd (build abcd)
+//
+// The VERSION format:
+//   "${MAJOR}.${MINOR}.${PATCH}"
+//   "${MAJOR}.${MINOR}.${PATCH}${UNKNOWN}"
+//   "${MAJOR}.${MINOR}.${PATCH}${UNKNOWN}-${PRE_RELEASE}"
+//   "${MAJOR}.${MINOR}.${PATCH}${UNKNOWN}-${PRE_RELEASE}+${BUILD_INFO}"
+//   "${MAJOR}.${MINOR}.${PATCH}${UNKNOWN}+${BUILD_INFO}"
+//   "${MAJOR}.${MINOR}.${PATCH}-${PRE_RELEASE}"
+//   "${MAJOR}.${MINOR}.${PATCH}-${PRE_RELEASE}+${BUILD_INFO}"
+//   "${MAJOR}.${MINOR}.${PATCH}+${BUILD_INFO}"
+//

Review comment:
       Thanks.
   I didn't think about parquet-mr's implementation. I've added some links.




----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

For queries about this service, please contact Infrastructure at:
users@infra.apache.org