patchwork_csv_utils 0.1.7-x86_64-darwin → 0.1.8-x86_64-darwin

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 6716d509dcd08fa0114772079eb4ee4c910d9fcba2e239292661f7394ae20579
-  data.tar.gz: 97b20c9b75784359b32bf352156827c62f1d63d29cb00833ce826ae9db1ba08a
+  metadata.gz: 6603f8bcfc0587d4d92642e938c58f3077e7cc22a3147de6cc11ad83f562d337
+  data.tar.gz: 4b8e33dcd5fa853d8f9a95420d6f844645dc552f16651e91458c6429f92b67b3
 SHA512:
-  metadata.gz: 4cb36630ed56de19331bc54206aaed38cfe1901b68ca4b4822c16d5141d8f0a7e374fa1c508b951dbf9182bcef3ffa5f2e0c8fa116b4ed63b148f6ebbddbf076
-  data.tar.gz: 5cc6c6c1a0edf9ef86b42fab23aaa2937b1a80fcad5518a1f15fd3fe22d0ace8d3a534bac85f46a83a25a1dadc6328d210806f616f561dc9fb5bbe712e2f5a8b
+  metadata.gz: a1102ac2ad779f7077324871702edb4597157715aae11fda27081c40dc6708aed94549053f4895ceb9dafcc862740de6b83b7cce09d770593bcf62dcb5fc1ed0
+  data.tar.gz: e33c5a1e1e521af86d6391093a7f0a5be3b77f733dad77e1114817aea944cd2788aa59b59b0aac94e0fbf82654ce0669c165f55966dc8d64ca0442b660becc22

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    patchwork_csv_utils (0.1.7)
+    patchwork_csv_utils (0.1.8)
 
 GEM
   remote: https://rubygems.org/
@@ -67,4 +67,4 @@ DEPENDENCIES
   rubocop (~> 1.21)
 
 BUNDLED WITH
-   2.4.4
+   2.4.10

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

@@ -19,6 +19,7 @@ pub fn transform_csv(ruby: &Ruby, csv_path: String, target_path: String, exclusi
     let mut wtr = Writer::from_path(target_path).map_err(|e| magnus_err(ruby, e, "target_path"))?;
     let headers = csv.headers().map_err(|e| magnus_err(ruby, e, "csv_path headers"))?;
     let header_map: HashMap<String, usize> = headers.iter().enumerate().map(|(i, h)| (h.to_string(), i)).collect();
+    let inverse_header_map: HashMap<usize, String> = headers.iter().enumerate().map(|(i, h)| (i, h.to_string())).collect();
 
     wtr.write_byte_record(headers.as_byte_record()).map_err(|e| magnus_err(ruby, e, "write_byte_record"))?;
 
@@ -41,11 +42,14 @@ pub fn transform_csv(ruby: &Ruby, csv_path: String, target_path: String, exclusi
         let record = record.iter().enumerate().map(|(i, c)| {
             let c = c.trim_end();
             if i == *date {
-                let current = string_to_datetime(c).ok_or(to_datetime_error(ruby, c, ri, i))?;
+                let current = string_to_datetime(c).ok_or(to_datetime_error(ruby, c, ri, "Date"))?;
                 date_value = current;
                 Ok(current.to_string())
             } else if i == *start || i == *end || i == *actual_start || i == *actual_end {
-                let current_time = string_to_time(c).ok_or(to_datetime_error(ruby, c, ri, i))?;
+                if c.is_empty() { return Ok(c.to_string()); }
+                let unknown = "Unknown".to_string();
+                let column_name = inverse_header_map.get(&i).unwrap_or(&unknown);
+                let current_time = string_to_time(c).ok_or(to_datetime_error(ruby, c, ri, column_name))?;
                 let datetime = transform_time_to_datetime(date_value, current_time);
                 Ok(datetime.to_string())
             } else {
@@ -79,7 +83,7 @@ fn transform_time_to_datetime(t1: NaiveDateTime, t2: NaiveTime) -> NaiveDateTime
     NaiveDateTime::new(t1.date(), t2)
 }
 
-fn to_datetime_error(ruby: &Ruby, value: &str, row: usize, col: usize) -> magnus::Error {
+fn to_datetime_error(ruby: &Ruby, value: &str, row: usize, col: &str) -> magnus::Error {
     magnus::Error::new(ruby.exception_standard_error(), format!("Could not parse datetime '{}', row: {}, col: {}", value, row, col))
 }
 

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

@@ -44,6 +44,9 @@ fn write_csv<W: Write>(ruby: &Ruby, dest: &mut W, range: &Range<Data>, header_ma
         if skip_excluded_rows(&request_id, r, &exclusions) { continue; }
         if skip_empty_rows(r) { continue; }
         if skip_rows_with_no_request_id(&request_id, r) { continue; }
+        if date_value_is_not_present(&date, r) {
+            return Err(magnus::Error::new(ruby.exception_standard_error(), format!("Date value is not present in row: {}", ri)));
+        }
 
         for (i, c) in r.iter().enumerate() {
             match *c {
@@ -53,7 +56,7 @@ fn write_csv<W: Write>(ruby: &Ruby, dest: &mut W, range: &Range<Data>, header_ma
                 }
                 Data::Float(ref f) => write!(dest, "{}", f),
                 Data::DateTime(ref d) => {
-                    let mut current = d.as_datetime().unwrap_or_default();
+                    let mut current = d.as_datetime().ok_or(to_datetime_error(ruby, &d.to_string(), ri, "Date"))?;
                     if i == *date {
                         date_value = current;
                     } else if i == *start || i == *end || i == *actual_start || i == *actual_end {
@@ -74,6 +77,10 @@ fn write_csv<W: Write>(ruby: &Ruby, dest: &mut W, range: &Range<Data>, header_ma
     Ok(())
 }
 
+fn date_value_is_not_present(date: &usize, r: &[Data]) -> bool {
+    r[*date] == Data::Empty
+}
+
 fn skip_excluded_rows(request_id: &usize, r: &[Data], exclusions: &Vec<String>) -> bool {
     let value = r[*request_id].to_string();
     exclusions.contains(&value.to_string())
@@ -91,6 +98,10 @@ fn transform_time_to_datetime(t1: NaiveDateTime, t2: NaiveDateTime) -> NaiveDate
     NaiveDateTime::new(t1.date(), t2.time())
 }
 
+fn to_datetime_error(ruby: &Ruby, value: &str, row: usize, col: &str) -> magnus::Error {
+    magnus::Error::new(ruby.exception_standard_error(), format!("Could not parse datetime '{}', row: {}, col: {}", value, row, col))
+}
+
 fn handle_commas<W: Write>(dest: &mut W, s: &str) -> std::io::Result<()> {
     if s.contains(",") {
         write!(dest, "{:?}", clean_strings(s).trim_end())

data/lib/csv_utils/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module CsvUtils
-  VERSION = '0.1.7'
+  VERSION = '0.1.8'
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: patchwork_csv_utils
 version: !ruby/object:Gem::Version
-  version: 0.1.7
+  version: 0.1.8
 platform: x86_64-darwin
 authors:
 - kingsley.hendrickse