[infer][java] for the buck integration, remove the files that are invalidating the Buck cache

Summary:
Sevel auxiliary files made it to the output directory of the analysis of individual targets when analyzing Java projects build with Buck. However, these files are then taken into account= to compute the target rule key and then to decide whether to analyze the dependent targets. Since these auxiliary files were containing time sentive information, every cach miss on a given target would then invalitate the cache entries for all the dependent targets.

This diff cleans up the output directory to only keep the specs files, the `global.tenv` and the `report.json` files which are the only artifacts needed to analyze the dependent targets

This diff makes a minimal number of changes to see how it behaves in prod, but I intend to refoctor this more when continuing to add support for running Infer with genrules

Reviewed By: sblackshear

Differential Revision: D4562615

fbshipit-source-id: 4628420

infer/src/backend/InferPrint.re

@@ -1401,6 +1401,8 @@ let main report_csv::report_csv report_json::report_json => {
     (Stats, init_stats_format_list ()),
     (Summary, init_summary_format_list ())
   ];
-  register_perf_stats_report ();
+  if (not Config.buck_cache_mode) {
+    register_perf_stats_report ()
+  };
   print_issues formats_by_report_kind
 };

infer/src/backend/infer.ml

@@ -120,8 +120,9 @@ let create_results_dir () =
   Unix.mkdir_p (Config.results_dir ^/ Config.specs_dir_name)
 
 let clean_results_dir () =
-  let dirs = ["classnames"; "filelists"; "multicore"; "sources"] in
-  let suffixes = [".cfg"; ".cg"] in
+  let dirs = ["classnames"; "filelists"; "multicore"; "sources"; "log";
+              "attributes"; "backend_stats"; "reporting_stats"; "frontend_stats"] in
+  let suffixes = [".cfg"; ".cg"; ".txt"; ".csv"; ".json"] in
   let rec clean name =
     match Unix.opendir name with
     | dir -> (
@@ -139,8 +140,13 @@ let clean_results_dir () =
               Unix.closedir dir in
         cleandir dir
       )
+    | exception Unix.Unix_error (Unix.ENOTDIR, _, _)
+      when String.equal (Filename.basename name) "report.json" ->
+        (* Keep the JSON report *)
+        ()
     | exception Unix.Unix_error (Unix.ENOTDIR, _, _) ->
-        if List.exists ~f:(Filename.check_suffix name) suffixes then
+        if not (String.equal (Filename.basename name) "report.json")
+        && List.exists ~f:(Filename.check_suffix name) suffixes then
           Unix.unlink name
     | exception Unix.Unix_error (Unix.ENOENT, _, _) ->
         () in
@@ -395,7 +401,7 @@ let () =
     remove_results_dir () ;
   create_results_dir () ;
   (* re-set log files, as default files were in results_dir removed above *)
-  L.set_log_file_identifier CLOpt.(Infer Driver) None ;
+  if not Config.buck_cache_mode then L.set_log_file_identifier CLOpt.(Infer Driver) None;
   if Config.print_builtins then Builtin.print_and_exit () ;
   if CLOpt.is_originator then L.do_out "%s@\n" Config.version_string ;
   if Config.debug_mode || Config.stats_mode then log_infer_args driver_mode ;
@@ -404,17 +410,19 @@ let () =
      anyway, pretend that we are not called from another make to prevent make falling back to a
      mono-threaded execution. *)
   Unix.unsetenv "MAKEFLAGS";
-  register_perf_stats_report () ;
-  touch_start_file () ;
+  if not Config.buck_cache_mode then register_perf_stats_report () ;
+  if Config.buck_cache_mode && Config.reactive_mode then
+    failwith "The reactive analysis mode is not compatible with the Buck integration for Java";
+  if not Config.buck_cache_mode then touch_start_file () ;
   capture driver_mode ;
   analyze driver_mode ;
   if CLOpt.is_originator then (
-    StatsAggregator.generate_files () ;
     let in_buck_mode = match driver_mode with | PythonCapture (BBuck, _) -> true | _ -> false in
+    StatsAggregator.generate_files () ;
     if Config.equal_analyzer Config.analyzer Config.Crashcontext then
       Crashcontext.crashcontext_epilogue ~in_buck_mode;
-    if in_buck_mode then
-      clean_results_dir () ;
     if Config.fail_on_bug then
       fail_on_issue_epilogue () ;
-  )
+  );
+  if Config.buck_cache_mode then
+    clean_results_dir ()

infer/src/base/Config.ml

@@ -1466,6 +1466,7 @@ and bootclasspath = !bootclasspath
 and bo_debug = !bo_debug
 and buck = !buck
 and buck_build_args = !buck_build_args
+and buck_cache_mode = !buck && not !debug
 and buck_out = !buck_out
 and bufferoverrun = !bufferoverrun
 and bugs_csv = !bugs_csv

infer/src/base/Config.mli

@@ -156,6 +156,7 @@ val bootclasspath : string option
 val bo_debug : int
 val buck : bool
 val buck_build_args : string list
+val buck_cache_mode : bool
 val buck_out : string option
 val bufferoverrun : bool
 val bugs_csv : string option

infer/src/java/jMain.ml

@@ -26,7 +26,7 @@ let register_perf_stats_report source_file =
 
 
 let init_global_state source_file =
-  register_perf_stats_report source_file ;
+  if not Config.buck_cache_mode then register_perf_stats_report source_file ;
   Config.curr_language := Config.Java;
   DB.Results_dir.init source_file;
   Ident.NameGenerator.reset ();

infer/tests/build_systems/genrule/module1/Class1.java

@@ -1,3 +1,12 @@
+/*
+ * Copyright (c) 2017 - present Facebook, Inc.
+ * All rights reserved.
+ *
+ * This source code is licensed under the BSD style license found in the
+ * LICENSE file in the root directory of this source tree. An additional grant
+ * of patent rights can be found in the PATENTS file in the same directory.
+ */
+
 package genrule.module1;
 
 import genrule.annotations.Nullable;

infer/tests/build_systems/genrule/module2/Class2.java

@@ -1,3 +1,12 @@
+/*
+ * Copyright (c) 2017 - present Facebook, Inc.
+ * All rights reserved.
+ *
+ * This source code is licensed under the BSD style license found in the
+ * LICENSE file in the root directory of this source tree. An additional grant
+ * of patent rights can be found in the PATENTS file in the same directory.
+ */
+
 package genrule.module2;
 
 import genrule.module1.Class1;