Added PDF parser to new morgan&stanley account statement documents (#96)

* - implemented recognition of PDF document types

* - excluded borkerage statement to seprate function

* - Writing parser for account statement (WIP)

* - Added sequnce parsing for div and tax of account statement

* - Added parsing (val) format of f32

* - Fixed taxation transaction

* - Fix to tax

* - quantity of stock is f32 now

* - Fixes to detection documents

* - Finished adding parser for new type of PDF (POC)

* - Added ignoring "$"

* - Added UT

* - Added tracing of legacy pdf documents parser

* - Partially done date parsing from new type of PDF

* - Implemented but does not work yet

* - All unit tests works e.g. implemented getting a fiscal date

* - Documents info updated

* - Added picture

* - removed deprecated TODOs

* - Added unit test (ignored e.g. depending on the locally stored data)

Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "etradeTaxReturnHelper"
-version = "0.4.0"
+version = "0.4.1"
 edition = "2021"
 description = "Parses etrade financial documents for transaction details  (income, tax paid, cost basis) and compute total income and total tax paid according to chosen tax residency (currency)"
 license = "BSD-3-Clause"

README.md

@@ -1,13 +1,16 @@
 # etradeTaxReturnHelper
-Project that parse e-trade PDF brokerage statements and Gain and Losses documents and compute total gross gain and tax paid in US that are needed for tax return forms out of US.
+Project that parse e-trade PDF account statements and Gain and Losses documents and compute total gross gain and tax paid in US that are needed for tax return forms out of US.
 
 ### Data for Tax form from capital gains (PIT-38 in Poland)
 1. Install this program: `cargo install etradeTaxReturnHelper`
-2. Download PDF documents from a year you are filling your tax return form for example: `Brokerage Statement <xxx>.pdf`:
+2. Download PDF documents from a year you are filling your tax return form for example: `Brokerage Statement <xxx>.pdf` and `MS_ClientStatements_<xxx>.pdf`:
     1. Login to e-trade, navigate to [Documents/Brokerage Statements](https://edoc.etrade.com/e/t/onlinedocs/docsearch?doc_type=stmt)
     2. Select date period
     3. Download all `ACCOUNT STATEMENT` documents
-3. Run: `etradeTaxReturnHelper <your PDF documents that MAY contains dividends and/or sold transactions e.g. "*.pdf">`
+3. Run: 
+    1. `etradeTaxReturnHelper <your PDF documents that MAY contains dividends and/or sold transactions e.g. "*.pdf"> <Gain and Loss XLSX document>`
+    2. Alternatively you can run `etradeTaxReturnHelper` to have program running with GUI (graphical user interface):
+       ![gui](/Pictures/GUI.png)
 
 ### FAQ
 1. How to install this project?
@@ -17,6 +20,9 @@ Project that parse e-trade PDF brokerage statements and Gain and Losses document
             `cargo install etradeTaxReturnHelper`
     3. For Linux where there is no X server or no priviligies to install system dependencies then you could try to install non-GUI version:
            `cargo install  etradeTaxReturnHelper --no-default-features`
+2. Does it work for other financial institutions apart from etrade ?
+   There is support for saving accounts statements of Revolut bank (CSV files) , as Revolut does not pay tax on customer behalf and tax from capital gain of saving account should be paid by customer. 
+
 
 2. How does it work?
     Here is a [demo(PL)](https://www.youtube.com/watch?v=Juw3KJ1JdcA)

src/lib.rs

@@ -265,7 +265,7 @@ pub fn run_taxation(
     String,
 > {
     let mut parsed_div_transactions: Vec<(String, f32, f32)> = vec![];
-    let mut parsed_sold_transactions: Vec<(String, String, i32, f32, f32)> = vec![];
+    let mut parsed_sold_transactions: Vec<(String, String, f32, f32, f32)> = vec![];
     let mut parsed_gain_and_losses: Vec<(String, String, f32, f32, f32)> = vec![];
     let mut parsed_revolut_transactions: Vec<(String, Currency)> = vec![];
 
@@ -274,15 +274,17 @@ pub fn run_taxation(
         // If name contains .pdf then parse as pdf
         // if name contains .xlsx then parse as spreadsheet
         if x.contains(".pdf") {
-            let (mut div_t, mut sold_t, _) = pdfparser::parse_brokerage_statement(x)?;
+            let (mut div_t, mut sold_t, _) = pdfparser::parse_statement(x)?;
             parsed_div_transactions.append(&mut div_t);
             parsed_sold_transactions.append(&mut sold_t);
         } else if x.contains(".xlsx") {
             parsed_gain_and_losses.append(&mut xlsxparser::parse_gains_and_losses(x)?);
-        } else {
+        } else if x.contains(".csv") {
             parsed_revolut_transactions.append(&mut csvparser::parse_revolut_transactions(x)?);
+        } else {
+            return Err(format!("Error: Unable to open a file: {x}"));
         }
-        Ok::<(), &str>(())
+        Ok::<(), String>(())
     })?;
     // 2. Verify Transactions
     verify_dividends_transactions(&parsed_div_transactions)?;

src/main.rs

@@ -11,8 +11,9 @@ mod gui;
 use etradeTaxReturnHelper::run_taxation;
 use logging::ResultExt;
 
-// TODO: Finish parse_revolut_transactions
-// TODO: Add UT for parsing investment document
+// TODO: Make a parsing of incomplete date
+// TODO: Dividends of revolut should combined with dividends not sold
+// TODO: When I sold on Dec there was EST cost (0.04). Make sure it is included in your results
 // TODO:  async to get currency
 // TODO: parse_gain_and_losses  expect ->  ?
 // TODO: GUI : choosing residency
@@ -327,6 +328,42 @@ mod tests {
         }
     }
 
+    #[test]
+    #[ignore]
+    fn test_sold_dividends_taxation_2023() -> Result<(), clap::Error> {
+        // Get all brokerage with dividends only
+        let myapp = App::new("E-trade tax helper").setting(AppSettings::ArgRequiredElseHelp);
+        let rd: Box<dyn etradeTaxReturnHelper::Residency> = Box::new(pl::PL {});
+
+        let matches = create_cmd_line_pattern(myapp).get_matches_from_safe(vec![
+            "mytest",
+            "etrade_data_2023/Brokerage Statement - XXXXX6557 - 202302.pdf",
+            "etrade_data_2023/Brokerage Statement - XXXXX6557 - 202303.pdf",
+            "etrade_data_2023/Brokerage Statement - XXXXX6557 - 202306.pdf",
+            "etrade_data_2023/Brokerage Statement - XXXXX6557 - 202308.pdf",
+            "etrade_data_2023/Brokerage Statement - XXXXX6557 - 202309.pdf",
+            "etrade_data_2023/MS_ClientStatements_6557_202309.pdf",
+            "etrade_data_2023/MS_ClientStatements_6557_202311.pdf",
+            "etrade_data_2023/MS_ClientStatements_6557_202312.pdf",
+            "etrade_data_2023/G&L_Collapsed-2023.xlsx",
+        ])?;
+        let pdfnames = matches
+            .values_of("financial documents")
+            .expect_and_log("error getting brokarage statements pdfs names");
+        let pdfnames: Vec<String> = pdfnames.map(|x| x.to_string()).collect();
+
+        match etradeTaxReturnHelper::run_taxation(&rd, pdfnames) {
+            Ok((gross_div, tax_div, gross_sold, cost_sold, _, _, _)) => {
+                assert_eq!(
+                    (gross_div, tax_div, gross_sold, cost_sold),
+                    (8369.726, 1253.2899, 14983.293, 7701.9253)
+                );
+                Ok(())
+            }
+            Err(x) => panic!("Error in taxation process"),
+        }
+    }
+
     #[test]
     #[ignore]
     fn test_sold_dividends_only_taxation() -> Result<(), clap::Error> {