add after-line and before-line command-line args

README.md

@@ -13,7 +13,7 @@ cargo run --release -- --raw-openstack data/openstack_normal2.log --to-parse "no
 cargo run --release -- --raw-hdfs data/HDFS_2k.log --to-parse "081109 204925 673 INFO dfs.DataNode$DataXceiver: Receiving block blk_-5623176793330377570 src: /10.251.75.228:53725 dest: /10.251.75.228:50010" --before "size <*>" --after "BLOCK* NameSystem.allocateBlock:"
 cargo run --release -- --raw-hpc data/HPC_2k.log --to-parse "inconsistent nodesets node-31 0x1fffffffe <ok> node-0 0xfffffffe <ok> node-1 0xfffffffe <ok> node-2 0xfffffffe <ok> node-30 0xfffffffe <ok>" --before "running running" --after "configured out"
 cargo run --release -- --raw-hpc data/HPC.log --to-parse "inconsistent nodesets node-31 0x1fffffffe <ok> node-0 0xfffffffe <ok> node-1 0xfffffffe <ok> node-2 0xfffffffe <ok> node-30 0xfffffffe <ok>" --before "running running" --after "configured out" --cutoff 106
-cargo run --release -- --raw-hpc data/HPC.log --to-parse "58717 2185 boot_cmd new 1076865186 1 Targeting domains:node-D1 and nodes:node-[40-63] child of command 2176" --before "command <*>" --after "Targeting domains" --cutoff 106
+cargo run --release -- --raw-hpc data/HPC.log --to-parse "58717 2185 boot_cmd new 1076865186 1 Targeting domains:node-D1 and nodes:node-[40-63] child of command 2176" --before-line "58728 2187 boot_cmd new 1076865197 1 Targeting domains:node-D2 and nodes:node-[72-95] child of command 2177" --after-line "58707 2184 boot_cmd new 1076865175 1 Targeting domains:node-D0 and nodes:node-[0-7] child of command 2175" --cutoff 106
 cargo run --release -- --raw-proxifier data/Proxifier_2k.log --to-parse "[10.30 16:54:08] chrome.exe - proxy.cse.cuhk.edu.hk:5070 close, 3637 bytes (3.55 KB) sent, 1432 bytes (1.39 KB) received, lifetime 00:01" --before "proxy.cse.cukh.edu.hk:5070 HTTPS" --after "open through" --cutoff 10
 cargo run --release -- --raw-healthapp data/HealthApp_2k.log --to-parse "20171223-22:15:41:672|Step_StandReportReceiver|30002312|REPORT : 7028 5017 150539 240" --before "calculateAltitudeWithCache totalAltitude=240" --after "onStandStepChanged 3601"
 cargo run --release -- --raw-healthapp data/HealthApp.log --to-parse "20171223-22:15:41:672|Step_StandReportReceiver|30002312|REPORT : 7028 5017 150539 240" --before "calculateAltitudeWithCache totalAltitude=240" --after "onStandStepChanged 3601" --cutoff 10

src/main.rs

@@ -49,6 +49,12 @@ struct Args {
    #[arg(long)]
    after: Option<String>,
 
+   #[arg(long)]
+   before_line: Option<String>,
+
+   #[arg(long)]
+   after_line: Option<String>,
+
    #[arg(long)]
    cutoff: Option<i32>,
 }
@@ -144,37 +150,30 @@ fn main() {
         None => panic!("no log format specified"),
     };
 
-    // let's say that the cutoff is 72 for Linux2k.log.
-    // check all of the 2-grams from the less-frequent 3-grams
-
-    // let mut two_grams = HashMap::new();
-    // let (val_set, reverse_d) = packages::parser::reverse_dict(&triple_dict);
-    // for val in val_set.iter().filter(|x| **x < CUTOFF) {
-    //     for key in reverse_d.get(val).unwrap() {
-    //         let val_2grams = derive_2grams_from_trigram(key);
-    //         for two_gram in val_2grams {
-    //             if let Some(count) = two_grams.get(&two_gram) {
-    //                 two_grams.insert(two_gram, count+1);
-    //             } else {
-    //                 two_grams.insert(two_gram, 1);
-    //             }
-    //         }
-    //     }
-    // }
-    // packages::parser::print_dict("inverted", &two_grams);
-
     //let sample_string = "Jun 23 23:30:05 combo sshd(pam_unix)[26190]: authentication failure; logname= uid=0 euid=0 tty=NODEVssh ruser= rhost=218.22.3.51  user=root authentication".to_string();
     // add befores and afters to the sample string, yielding extended_sample_string
     let mut sample_string_tokens = packages::parser::token_splitter(args.to_parse, 
                                                                     &format_string_re,
                                                                     &censored_regexps);
-    let mut befores = match args.before {
-        None => vec![],
-        Some(b) => b.split_whitespace().map(|s| s.to_string()).collect(),
+    let mut befores = match (args.before, args.before_line) {
+        (None, None) => vec![],
+        (Some(b), None) => b.split_whitespace().map(|s| s.to_string()).collect(),
+        (None, Some(b)) | (Some(_), Some(b)) => {
+            let r = packages::parser::token_splitter(b,
+                                                     &format_string_re,
+                                                     &censored_regexps);
+            r[r.len()-2..r.len()].to_vec()
+        }
     };
-    let mut afters = match args.after {
-        None => vec![],
-        Some(a) => a.split_whitespace().map(|s| s.to_string()).collect(),
+    let mut afters = match (args.after, args.after_line) {
+        (None, None) => vec![],
+        (Some(a), None) => a.split_whitespace().map(|s| s.to_string()).collect(),
+        (None, Some(a)) | (Some(_), Some(a)) => {
+            let r = packages::parser::token_splitter(a,
+                                                     &format_string_re,
+                                                     &censored_regexps);
+            r[0..2].to_vec()
+        }
     };
 
     let mut extended_sample_string_tokens = vec![];