Added cleaning up of funny descriptions

Mostly branches and dates messing with import matching

4 files changed, 142 insertions, 6 deletions

diff --git a/Cargo.lock b/Cargo.lock
index ad707a0..4d21764 100644
--- a/Cargo.lock
+++ b/Cargo.lock
@@ -1,4 +1,95 @@
 [root]
 name = "qif_parser"
 version = "0.1.0"
+dependencies = [
+ "lazy_static 1.0.0 (registry+https://github.com/rust-lang/crates.io-index)",
+ "regex 0.2.2 (registry+https://github.com/rust-lang/crates.io-index)",
+]
 
+[[package]]
+name = "aho-corasick"
+version = "0.6.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+dependencies = [
+ "memchr 1.0.2 (registry+https://github.com/rust-lang/crates.io-index)",
+]
+
+[[package]]
+name = "lazy_static"
+version = "0.2.11"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+
+[[package]]
+name = "lazy_static"
+version = "1.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+
+[[package]]
+name = "libc"
+version = "0.2.33"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+
+[[package]]
+name = "memchr"
+version = "1.0.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+dependencies = [
+ "libc 0.2.33 (registry+https://github.com/rust-lang/crates.io-index)",
+]
+
+[[package]]
+name = "regex"
+version = "0.2.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+dependencies = [
+ "aho-corasick 0.6.3 (registry+https://github.com/rust-lang/crates.io-index)",
+ "memchr 1.0.2 (registry+https://github.com/rust-lang/crates.io-index)",
+ "regex-syntax 0.4.1 (registry+https://github.com/rust-lang/crates.io-index)",
+ "thread_local 0.3.4 (registry+https://github.com/rust-lang/crates.io-index)",
+ "utf8-ranges 1.0.0 (registry+https://github.com/rust-lang/crates.io-index)",
+]
+
+[[package]]
+name = "regex-syntax"
+version = "0.4.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+
+[[package]]
+name = "thread_local"
+version = "0.3.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+dependencies = [
+ "lazy_static 0.2.11 (registry+https://github.com/rust-lang/crates.io-index)",
+ "unreachable 1.0.0 (registry+https://github.com/rust-lang/crates.io-index)",
+]
+
+[[package]]
+name = "unreachable"
+version = "1.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+dependencies = [
+ "void 1.0.2 (registry+https://github.com/rust-lang/crates.io-index)",
+]
+
+[[package]]
+name = "utf8-ranges"
+version = "1.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+
+[[package]]
+name = "void"
+version = "1.0.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+
+[metadata]
+"checksum aho-corasick 0.6.3 (registry+https://github.com/rust-lang/crates.io-index)" = "500909c4f87a9e52355b26626d890833e9e1d53ac566db76c36faa984b889699"
+"checksum lazy_static 0.2.11 (registry+https://github.com/rust-lang/crates.io-index)" = "76f033c7ad61445c5b347c7382dd1237847eb1bce590fe50365dcb33d546be73"
+"checksum lazy_static 1.0.0 (registry+https://github.com/rust-lang/crates.io-index)" = "c8f31047daa365f19be14b47c29df4f7c3b581832407daabe6ae77397619237d"
+"checksum libc 0.2.33 (registry+https://github.com/rust-lang/crates.io-index)" = "5ba3df4dcb460b9dfbd070d41c94c19209620c191b0340b929ce748a2bcd42d2"
+"checksum memchr 1.0.2 (registry+https://github.com/rust-lang/crates.io-index)" = "148fab2e51b4f1cfc66da2a7c32981d1d3c083a803978268bb11fe4b86925e7a"
+"checksum regex 0.2.2 (registry+https://github.com/rust-lang/crates.io-index)" = "1731164734096285ec2a5ec7fea5248ae2f5485b3feeb0115af4fda2183b2d1b"
+"checksum regex-syntax 0.4.1 (registry+https://github.com/rust-lang/crates.io-index)" = "ad890a5eef7953f55427c50575c680c42841653abd2b028b68cd223d157f62db"
+"checksum thread_local 0.3.4 (registry+https://github.com/rust-lang/crates.io-index)" = "1697c4b57aeeb7a536b647165a2825faddffb1d3bad386d507709bd51a90bb14"
+"checksum unreachable 1.0.0 (registry+https://github.com/rust-lang/crates.io-index)" = "382810877fe448991dfc7f0dd6e3ae5d58088fd0ea5e35189655f84e6814fa56"
+"checksum utf8-ranges 1.0.0 (registry+https://github.com/rust-lang/crates.io-index)" = "662fab6525a98beff2921d7f61a39e7d59e0b425ebc7d0d9e66d316e55124122"
+"checksum void 1.0.2 (registry+https://github.com/rust-lang/crates.io-index)" = "6a02e4885ed3bc0f2de90ea6dd45ebcbb66dacffe03547fadbb0eeae2770887d"
diff --git a/Cargo.toml b/Cargo.toml
index 7c48e58..62e16be 100644
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -4,3 +4,5 @@ version = "0.1.0"
 authors = ["Justin Worthe <justin@worthe-it.co.za>"]
 
 [dependencies]
+regex = "0.2.2"
+lazy_static = "1.0"
\ No newline at end of file
diff --git a/src/lib.rs b/src/lib.rs
index 51368c5..7cb52d0 100644
--- a/src/lib.rs
+++ b/src/lib.rs
@@ -1 +1,5 @@
+extern crate regex;
+
+#[macro_use] extern crate lazy_static;
+
 pub mod qif;
diff --git a/src/qif.rs b/src/qif.rs
index 46b2bc3..41f8e6f 100644
--- a/src/qif.rs
+++ b/src/qif.rs
@@ -1,4 +1,5 @@
 use std::fmt;
+use regex::Regex;
 
 pub struct QifFile {
     header: String,
@@ -54,23 +55,61 @@ impl QifEntry {
         let amount = lines.iter().find(|l| l.starts_with(AMOUNT_PREFIX)).expect("No amount");
         let description = lines.iter().find(|l| l.starts_with(DESCRIPTION_PREFIX)).expect("No description");
         QifEntry {
-            date: date.clone(),
-            amount: amount.clone(),
-            description: description.clone()
+            date: date.chars().skip(1).collect(),
+            amount: amount.chars().skip(1).collect(),
+            description: description.chars().skip(1).collect()
         }
     }
 
     pub fn is_empty(&self) -> bool {
-        self.amount == String::from("T0")
+        self.amount == String::from("0")
     }
 
     pub fn clean_description(&self) -> String {
-        self.description.clone()
+        let replaced_date = replace_date(&self.description);
+        replace_common(&replaced_date)
     }
 }
 
 impl fmt::Display for QifEntry {
     fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
-        write!(f, "{}\n{}\n{}", self.date, self.amount, self.clean_description())
+        write!(f, "{}{}\n{}{}\n{}{}",
+               DATE_PREFIX, self.date,
+               AMOUNT_PREFIX, self.amount,
+               DESCRIPTION_PREFIX, self.clean_description()
+        )
     }
 }
+
+fn replace_date(text: &str) -> String {
+    lazy_static! {
+        static ref DATE_REGEX: Regex = Regex::new(r"(?i)(\d{2} )?(JAN|FEB|MAR|APR|MAY|JUN|JUL|AUG|SEP|OCT|NOV|DEC)( \d{4})?").unwrap();
+    }
+    DATE_REGEX.replace_all(text, "").trim().to_string()
+}
+
+fn replace_common(text: &str) -> String {
+    lazy_static! {
+        static ref COMMON_NAMES: Vec<(Regex, &'static str)> = vec!(
+            (Regex::new(r"(?i)(pick n pay|pnp)").unwrap(), "Pick n Pay"),
+            (Regex::new(r"(?i)checkers").unwrap(), "Checkers"),
+            (Regex::new(r"(?i)WOOLWORTHS").unwrap(), "Woolworths"),
+            (Regex::new(r"(?i)spar").unwrap(), "Spar"),
+            (Regex::new(r"(?i)Crazy store").unwrap(), "Crazy Store"),
+            (Regex::new(r"^PNA").unwrap(), "PNA"),
+            (Regex::new(r"(?i)sahl").unwrap(), "SA Home Loans"),
+            (Regex::new(r"(?i)gautrain").unwrap(), "Gautrain"),
+            (Regex::new(r"(?i)BANK YOUR CHANGE DEBI").unwrap(), "TO SAVINGS POCKET"),
+            (Regex::new(r"(?i)AFRIHOST").unwrap(), "Afrihost"),
+            (Regex::new(r"(?i)DIALDIRECT").unwrap(), "Dialdirect"),
+            (Regex::new(r"(?i)STEERS").unwrap(), "Steers"),
+            (Regex::new(r"(?i)CELL C").unwrap(), "Cell C"),
+            (Regex::new(r"(?i)ELECTRICITY").unwrap(), "Electricity"),
+            (Regex::new(r"(?i)(COUNTRY VIEW|STAR STOP|Shell|Sasol)").unwrap(), "Petrol"),
+        );
+    }
+    COMMON_NAMES.iter().fold(
+        text, |acc, next| if next.0.is_match(acc) {next.1} else {acc}
+    ).to_string()
+}
+