patchwork_csv_utils 0.1.21-arm64-darwin → 0.1.23-arm64-darwin

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: eb9ba1cfb3930c7586b62182de0c6c9a2f1207d186bf1a7a2c578a8cfc294bf7
-  data.tar.gz: aec2801daf163c9de70c96d77aaabf62feaa70483785afed01b12d8546fd069b
+  metadata.gz: ff496709a23c4cfeba6216aef09b3feb5b32609362b45cdd269e8b1e3d610adc
+  data.tar.gz: 21d6e4dd7e4cb58150b46c8efb771a6f864d19c20b6c57b7fa9d79ecd303b69b
 SHA512:
-  metadata.gz: e79a8ae7df6fb41bfb309d89faf850a9122b60c0754ef58736fabc684964eda9e7b7b2a6a1e6948fd107ede13275ba636d7b4e56212425da35582c1d16a7befc
-  data.tar.gz: e4f7e61799ef6dc6153acb32dd4ecc589671a96e40c95c71e92105ad199a9a6b75f05631a10b6fb13389937c665513ef1d96e6edbf1833bbff3defe174896a68
+  metadata.gz: 3b4d883cf490921a2365f70785eff0673d01cf4be369350b1953d83c7a9a39b81290bcac66d6747484d7ae37d4c4a491ac49b6ce9a644e67cd1c66e735cc74f6
+  data.tar.gz: e4703bc008ffbbe68fa02fd4eea982e29da38e07c4df0c1d776e71e921b2475bcf4dc91f076907827448e8e106493be7e4cb5fc7e8af5d955ff1856381a48afe

data/.ruby-version

@@ -0,0 +1 @@
+ruby-3.0.7

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    patchwork_csv_utils (0.1.21)
+    patchwork_csv_utils (0.1.23)
 
 GEM
   remote: https://rubygems.org/
@@ -56,6 +56,7 @@ GEM
 PLATFORMS
   arm64-darwin-22
   arm64-darwin-23
+  arm64-darwin-24
   x86_64-linux
 
 DEPENDENCIES

data/ext/csv_utils/src/lib.rs

@@ -9,7 +9,7 @@ pub mod utils;
 fn init() -> Result<(), magnus::Error> {
     let module = define_module("CsvUtils")?;
     module.define_singleton_method("dedup", function!(dedup, 4))?;
-    module.define_singleton_method("to_csv", function!(to_csv, 7))?;
-    module.define_singleton_method("transform_csv", function!(transform_csv, 7))?;
+    module.define_singleton_method("to_csv", function!(to_csv, 8))?;
+    module.define_singleton_method("transform_csv", function!(transform_csv, 8))?;
     Ok(())
 }

data/ext/csv_utils/src/utils/csv.rs

@@ -1,21 +1,27 @@
-use chrono::{NaiveDate, NaiveDateTime, NaiveTime, Utc};
+use chrono::{NaiveDateTime, NaiveTime, Utc};
 use csv::{Reader, StringRecord, Writer};
 use magnus::{Error, RArray, Ruby};
 use std::collections::HashMap;
 use std::fs::File;
 
-use crate::utils::{check_mandatory_headers, create_header_map, headers_as_byte_record, index_of_header_in_mandatory_list, magnus_err, missing_header, missing_value, to_datetime_error, FileExtension};
+use crate::utils::{check_mandatory_headers, correct_datetime, create_header_map, headers_as_byte_record, index_of_header_in_mandatory_list, magnus_err, missing_header, missing_value, string_to_datetime, to_datetime_error, FileExtension};
 
-pub fn transform_csv(ruby: &Ruby, csv_path: String,
-                     target_path: String, exclusions: RArray,
+pub fn transform_csv(ruby: &Ruby,
+                     csv_path: String,
+                     target_path: String,
+                     exclusions: RArray,
                      mandatory_headers: RArray,
                      status_exclusions: RArray,
                      expected_trust_name: String,
-                     is_streamed_file: bool) -> magnus::error::Result<()> {
+                     is_streamed_file: bool,
+                     earliest_start_date: Option<String>) -> magnus::error::Result<()> {
     if !csv_path.has_extension(&["csv"]) {
         return Err(Error::new(ruby.exception_standard_error(), "csv_path must be a csv file".to_string()));
     }
 
+    let start_date = earliest_start_date
+        .and_then(|date_str| string_to_datetime(&date_str));
+
     let exclusions = RArray::to_vec(exclusions)?;
     let status_exclusions = RArray::to_vec(status_exclusions)?;
     let mandatory_headers: Vec<String> = RArray::to_vec(mandatory_headers)?;
@@ -48,7 +54,8 @@ pub fn transform_csv(ruby: &Ruby, csv_path: String,
 
     for (ri, record) in mandatory_records.iter().enumerate() {
 
-        if skip_excluded_rows(request_id, &record, &exclusions) { continue; }
+        if skip_rows_before_start_date(&start_date, &record, &date) { continue; }
+        if skip_excluded_rows(request_id, &status, &record, &exclusions) { continue; }
         if skip_excluded_status_rows(&status, &record, &status_exclusions) { continue; }
         if has_empty_row_skip(&record) { continue; }
         if has_empty_first_col_skip_row(&record) { continue; }
@@ -140,27 +147,36 @@ fn get_column_name(inverse_header_map: &HashMap<usize, String>, i: &usize) -> St
     column_name.to_string()
 }
 
-fn skip_excluded_rows(request_id: &usize, r: &StringRecord, exclusions: &Vec<String>) -> bool {
+fn skip_excluded_rows(request_id: &usize, status: &Option<&usize>, r: &StringRecord, exclusions: &Vec<String>) -> bool {
+    if let Some(status_index) = status {
+        if let Some(status) = r.get(**status_index) {
+            if status.eq("Recalled") {
+                return false
+            }
+        }
+    }
+
     let value = r.get(*request_id).unwrap_or_default();
     exclusions.contains(&value.to_string())
 }
 
+fn skip_rows_before_start_date(&start_date: &Option<NaiveDateTime>, r: &StringRecord, date_index: &usize) -> bool {
+    if let Some(start_date) = start_date {
+        if let Some(date_str) = r.get(*date_index) {
+            if let Some(date) = string_to_datetime(date_str) {
+                return date <= start_date;
+            }
+        }
+    }
+    false
+}
+
 fn skip_excluded_status_rows(status: &Option<&usize>, r: &StringRecord, exclusions: &Vec<String>) -> bool {
     status
         .map(|index| exclusions.contains(&r[*index].to_string()))
         .unwrap_or(false)
 }
 
-fn string_to_datetime(s: &str) -> Option<NaiveDateTime> {
-    let maybe_correct = correct_datetime(s);
-    if maybe_correct.is_some() { return maybe_correct; }
-
-    NaiveDate::parse_from_str(s, "%d-%b-%y").ok().map(|d| d.and_hms_opt(0, 0, 0)).flatten()
-}
-
-fn correct_datetime(s: &str) -> Option<NaiveDateTime> {
-    NaiveDateTime::parse_from_str(s, "%Y-%m-%d %H:%M:%S").ok()
-}
 
 fn string_to_time(s: &str) -> Option<NaiveTime> {
     NaiveTime::parse_from_str(s, "%H:%M").ok()

data/ext/csv_utils/src/utils/mod.rs

@@ -4,6 +4,7 @@ use std::ffi::OsStr;
 use std::path::Path;
 use ::csv::{ByteRecord, StringRecord};
 use magnus::Ruby;
+use chrono::{NaiveDate, NaiveDateTime};
 
 pub mod csv;
 pub mod dedup;
@@ -83,3 +84,19 @@ impl<P: AsRef<Path>> FileExtension for P {
     }
 }
 
+pub fn string_to_datetime(s: &str) -> Option<NaiveDateTime> {
+    let maybe_correct = correct_datetime(s);
+    if maybe_correct.is_some() { return maybe_correct; }
+
+    // Try YYYY-MM-DD format
+    if let Ok(date) = NaiveDate::parse_from_str(s, "%Y-%m-%d") {
+        return date.and_hms_opt(0, 0, 0);
+    }
+
+    NaiveDate::parse_from_str(s, "%d-%b-%y").ok().map(|d| d.and_hms_opt(0, 0, 0)).flatten()
+}
+
+pub fn correct_datetime(s: &str) -> Option<NaiveDateTime> {
+    NaiveDateTime::parse_from_str(s, "%Y-%m-%d %H:%M:%S").ok()
+}
+

data/ext/csv_utils/src/utils/xls.rs

@@ -2,11 +2,11 @@ use std::collections::HashMap;
 use std::fs::File;
 use std::io::{BufWriter, Write};
 
-use calamine::{open_workbook_auto, Data, Range, Reader};
+use calamine::{open_workbook_auto, Data, DataType, Range, Reader};
 use chrono::{NaiveDateTime, Timelike, Utc};
 use magnus::{RArray, Ruby};
 
-use crate::utils::{check_mandatory_headers, index_of_header_in_mandatory_list, magnus_err, missing_header, missing_value, to_datetime_error, FileExtension};
+use crate::utils::{check_mandatory_headers, index_of_header_in_mandatory_list, magnus_err, missing_header, missing_value, string_to_datetime, to_datetime_error, FileExtension};
 
 pub fn to_csv(ruby: &Ruby, xls_path: String,
               target_path: String,
@@ -14,7 +14,8 @@ pub fn to_csv(ruby: &Ruby, xls_path: String,
               mandatory_headers: RArray,
               status_exclusions: RArray,
               expected_trust_name: String,
-              is_streamed_file: bool
+              is_streamed_file: bool,
+              earliest_start_date: Option<String>
 ) -> magnus::error::Result<()> {
     if !xls_path.has_extension(&["xls","xlsx"]) {
         return Err(magnus::Error::new(ruby.exception_standard_error(), "xls_path must be an xls or xlsx file".to_string()));
@@ -23,6 +24,9 @@ pub fn to_csv(ruby: &Ruby, xls_path: String,
     let exclusions = RArray::to_vec(exclusions)?;
     let mandatory_headers: Vec<String> = RArray::to_vec(mandatory_headers)?;
     let status_exclusions = RArray::to_vec(status_exclusions)?;
+    
+    let start_date = earliest_start_date
+        .and_then(|date_str| string_to_datetime(&date_str));
 
     let mut workbook = open_workbook_auto(&xls_path)
         .map_err(|e| magnus_err(ruby, e, format!("could not open workbook: {}", xls_path).as_str()))?;
@@ -41,7 +45,7 @@ pub fn to_csv(ruby: &Ruby, xls_path: String,
     let csv_out_file = File::create(target_path.clone()).map_err(|e| magnus_err(ruby, e, format!("could not create csv file: {}", target_path).as_str()))?;
     let mut dest = BufWriter::new(csv_out_file);
 
-    write_csv(ruby, &mut dest, &range, header_map, exclusions, mandatory_headers, headers_list, status_exclusions, expected_trust_name, is_streamed_file)
+    write_csv(ruby, &mut dest, &range, header_map, exclusions, mandatory_headers, headers_list, status_exclusions, expected_trust_name, is_streamed_file, start_date)
 }
 
 fn write_csv<W: Write>(ruby: &Ruby, dest: &mut W, range: &Range<Data>,
@@ -50,7 +54,8 @@ fn write_csv<W: Write>(ruby: &Ruby, dest: &mut W, range: &Range<Data>,
                        headers_list: Vec<String>,
                        status_exclusions: Vec<String>,
                        expected_trust_name: String,
-                       is_streamed_file: bool) -> magnus::error::Result<()> {
+                       is_streamed_file: bool,
+                       start_date: Option<NaiveDateTime>) -> magnus::error::Result<()> {
     let n = mandatory_headers.len() - 1;
     let request_id = header_map.get("Request Id").ok_or(missing_header(ruby, "Request Id"))?;
     let date = header_map.get("Date").ok_or(missing_header(ruby, "Date"))?;
@@ -66,7 +71,8 @@ fn write_csv<W: Write>(ruby: &Ruby, dest: &mut W, range: &Range<Data>,
     for (ri, r) in mandatory_rows.into_iter().enumerate() {
         let mut date_value = Utc::now().naive_utc();
 
-        if skip_excluded_rows(&request_id, &r, &exclusions) { continue; }
+        if skip_rows_before_start_date(&start_date, &r, &date) { continue; }
+        if skip_excluded_rows(&request_id, &status, &r, &exclusions) { continue; }
         if skip_excluded_status_rows(&status, &r, &status_exclusions) { continue; }
         if skip_empty_rows(&r) { continue; }
         if skip_rows_with_no_request_id(&request_id, &r) { continue; }
@@ -185,7 +191,17 @@ fn date_value_is_not_present(date: &usize, r: &Vec<&Data>) -> bool {
     r[*date] == &Data::Empty
 }
 
-fn skip_excluded_rows(request_id: &usize, r: &Vec<&Data>, exclusions: &Vec<String>) -> bool {
+fn skip_excluded_rows(request_id: &usize, status: &Option<&usize>, r: &Vec<&Data>, exclusions: &Vec<String>) -> bool {
+    if let Some(status_index) = status {
+        if let Some(status) = r.get(**status_index) {
+            if let Some(status_str) = status.as_string() {
+                if status_str.eq("Recalled") {
+                    return false
+                }
+            }
+        }
+    }
+
     let value = r[*request_id].to_string();
     exclusions.contains(&value.to_string())
 }
@@ -204,6 +220,27 @@ fn skip_rows_with_no_request_id(request_id: &usize, r: &Vec<&Data>) -> bool {
     r[*request_id] == &Data::Empty
 }
 
+fn skip_rows_before_start_date(start_date: &Option<NaiveDateTime>, r: &Vec<&Data>, date_index: &usize) -> bool {
+    if let Some(start_date) = start_date {
+        if let Some(date_data) = r.get(*date_index) {
+            match date_data {
+                Data::DateTime(d) => {
+                    if let Some(date) = d.as_datetime() {
+                        return date <= *start_date;
+                    }
+                }
+                Data::DateTimeIso(s) => {
+                    if let Some(date) = string_to_datetime(s) {
+                        return date <= *start_date;
+                    }
+                }
+                _ => {}
+            }
+        }
+    }
+    false
+}
+
 fn transform_time_to_datetime(t1: NaiveDateTime, t2: NaiveDateTime) -> NaiveDateTime {
     NaiveDateTime::new(t1.date(), t2.time())
 }

data/lib/csv_utils/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module CsvUtils
-  VERSION = '0.1.21'
+  VERSION = '0.1.23'
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: patchwork_csv_utils
 version: !ruby/object:Gem::Version
-  version: 0.1.21
+  version: 0.1.23
 platform: arm64-darwin
 authors:
 - kingsley.hendrickse
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2025-04-14 00:00:00.000000000 Z
+date: 2025-07-08 00:00:00.000000000 Z
 dependencies: []
 description: Deduplication of CSV files and XLS to CSV conversion.
 email:
@@ -19,6 +19,7 @@ extra_rdoc_files: []
 files:
 - ".rspec"
 - ".rubocop.yml"
+- ".ruby-version"
 - Cargo.lock
 - Cargo.toml
 - Gemfile