philiprehberger-csv_kit 0.8.0 → 0.10.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: c48c099081a08bc9be83c75fb8879f9cb876ce2cc6e8978a44b8c18d3cd43776
-  data.tar.gz: fe72a612c3a6e5b0166c5eb24694f5593cbb0baca3eb541081dc84414939019b
+  metadata.gz: 2ad7f9f8f543aa7336129a60b131b397f7d46884dc63949aed97ffcdeea41a99
+  data.tar.gz: 623d9169efd50e7f1bf3894c7a6b7ffbc99c79085a444d633c280af727f0f8b6
 SHA512:
-  metadata.gz: bfff72e557a3deef83f104118ec4dddf00e5855b2d29ea1ac09a023f767a3b557f7415a9b8fd953ddca68a5cc08155b4b37b14a1800b3f2672db059b1a8a02da
-  data.tar.gz: a2bd950d995457677e70c2398efb4decb742597bc032e5f0f0454ac5a9025d4a41c2d05f4bcf18988f506c46ffdd0b20b354b7620748587c3de7e32da75387d7
+  metadata.gz: aaee8ffddffaabf495a59a9e5b7b00d2ebfbcc73f06d73229f96c11184f16c7215203ead52e77c1bc109e29d8eb28e2b2b5e728c64d094bb35af953a5c62aad7
+  data.tar.gz: a310d1904161f42549cff7b2dfee711d2f483e6b2cb9ff5428267e9118bdc80130af7b701b47ad6e659c56dddb29607f7b6d5eea0af6dd0e667b207e0fc2e765

data/CHANGELOG.md

@@ -7,6 +7,16 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [0.10.0] - 2026-05-07
+
+### Added
+- `CsvKit.transpose(path_or_io, dialect:)` — returns a column-oriented hash mapping each header to the array of values across all rows. The natural complement to `to_hashes` for column-wise operations.
+
+## [0.9.0] - 2026-04-19
+
+### Added
+- `Processor#default(key, value)` — fill nil or empty cells at `key` with a default value during transform; chains naturally with `type:` coercion
+
 ## [0.8.0] - 2026-04-17
 
 ### Added
@@ -107,7 +117,9 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Type coercion and row validation
 - Quick load and filtering convenience methods
 
-[Unreleased]: https://github.com/philiprehberger/rb-csv-kit/compare/v0.8.0...HEAD
+[Unreleased]: https://github.com/philiprehberger/rb-csv-kit/compare/v0.10.0...HEAD
+[0.10.0]: https://github.com/philiprehberger/rb-csv-kit/releases/tag/v0.10.0
+[0.9.0]: https://github.com/philiprehberger/rb-csv-kit/compare/v0.8.0...v0.9.0
 [0.8.0]: https://github.com/philiprehberger/rb-csv-kit/compare/v0.7.0...v0.8.0
 [0.7.0]: https://github.com/philiprehberger/rb-csv-kit/compare/v0.6.0...v0.7.0
 [0.6.0]: https://github.com/philiprehberger/rb-csv-kit/compare/v0.5.0...v0.6.0

data/README.md

@@ -106,6 +106,17 @@ rows = Philiprehberger::CsvKit.process("data.csv") do |p|
 end
 ```
 
+### Default Values for Missing Cells
+
+Fill nil or empty-string cells with a default value before any `type` coercion runs:
+
+```ruby
+Philiprehberger::CsvKit.process("users.csv") do |p|
+  p.default(:country, "US")
+  p.type(:age, :integer)
+end
+```
+
 ### Date/Time Type Coercions
 
 ```ruby
@@ -194,11 +205,25 @@ delimiter = Philiprehberger::CsvKit::Detector.detect("data.tsv")
 # => "\t"
 ```
 
+### Column Transpose
+
+```ruby
+require 'philiprehberger/csv_kit'
+
+# users.csv:
+# name,age
+# Alice,30
+# Bob,25
+Philiprehberger::CsvKit.transpose('users.csv')
+# => { name: ['Alice', 'Bob'], age: ['30', '25'] }
+```
+
 ## API
 
 | Method / Class | Description |
 |----------------|-------------|
 | `CsvKit.to_hashes(path_or_io, dialect:)` | Load CSV into array of symbolized hashes |
+| `CsvKit.transpose(path_or_io, dialect:)` | Returns a column-oriented hash mapping each header to its column of values |
 | `CsvKit.to_csv(rows, headers:, dialect:)` | Serialize an array of hashes to a CSV string |
 | `CsvKit.sample(path_or_io, n, dialect:)` | Return n randomly sampled rows using reservoir sampling (Algorithm R) |
 | `CsvKit.pluck(path_or_io, *keys, dialect:)` | Extract specific columns |
@@ -211,6 +236,7 @@ delimiter = Philiprehberger::CsvKit::Detector.detect("data.tsv")
 | `Processor#headers(*names)` | Override header names |
 | `Processor#transform(key, &block)` | Register column transform |
 | `Processor#type(key, type, **opts)` | Register built-in type coercion (:integer, :float, :string, :date, :datetime) |
+| `Processor#default(key, value)` | Fill nil or empty cells at `key` with `value` (runs before `type` coercion) |
 | `Processor#validate(key, &block)` | Register column validation (skip invalid) |
 | `Processor#skip(n)` | Skip the first N data rows |
 | `Processor#limit(n)` | Stop after processing N rows |

data/lib/philiprehberger/csv_kit/processor.rb

@@ -31,6 +31,7 @@ module Philiprehberger
         @path_or_io = path_or_io
         @dialect = dialect ? Dialect.new(dialect) : nil
         @transforms = {}
+        @defaults = {}
         @validations = {}
         @reject_block = nil
         @each_block = nil
@@ -63,6 +64,22 @@ module Philiprehberger
         @transforms[key] = ->(v) { coercion.call(v, opts) }
       end
 
+      # Register a default value for a column.
+      #
+      # Cells where the value is `nil` or an empty string are replaced with
+      # the provided default during transform. Defaults run BEFORE `type`
+      # coercions and `transform` blocks, so callers can default a missing
+      # cell to a string and then coerce it (e.g. default to "0" then cast
+      # to :integer).
+      #
+      # @param key [Symbol] column name
+      # @param value [Object] value to use when the cell is nil or empty
+      # @return [self]
+      def default(key, value)
+        @defaults[key] = value
+        self
+      end
+
       # Register a validation for a specific column.
       def validate(key, &block)
         @validations[key] = block
@@ -122,6 +139,7 @@ module Philiprehberger
         return unless valid?(row)
         return if rejected?(row)
 
+        apply_defaults!(row)
         apply_transforms!(row)
         apply_renames!(row)
         @each_block&.call(row)
@@ -165,6 +183,13 @@ module Philiprehberger
         @reject_block&.call(row) || false
       end
 
+      def apply_defaults!(row)
+        @defaults.each do |key, value|
+          current = row[key]
+          row[key] = value if current.nil? || current.to_s.empty?
+        end
+      end
+
       def apply_transforms!(row)
         @transforms.each { |key, blk| row[key] = blk.call(row[key]) }
       end

data/lib/philiprehberger/csv_kit/version.rb

@@ -2,6 +2,6 @@
 
 module Philiprehberger
   module CsvKit
-    VERSION = '0.8.0'
+    VERSION = '0.10.0'
   end
 end

data/lib/philiprehberger/csv_kit.rb

@@ -42,6 +42,20 @@ module Philiprehberger
       rows
     end
 
+    # Read a CSV and return a hash mapping each header to the column of values.
+    #
+    # @param path_or_io [String, IO] the path or IO to read from
+    # @param dialect [Hash, nil] optional CSV dialect overrides
+    # @return [Hash{Symbol => Array}] column-oriented view of the CSV
+    def self.transpose(path_or_io, dialect: nil)
+      rows = to_hashes(path_or_io, dialect: dialect)
+      return {} if rows.empty?
+
+      rows.first.keys.to_h do |key|
+        [key, rows.map { |row| row[key] }]
+      end
+    end
+
     # Serialize an array of hashes to a CSV string.
     #
     # If headers is omitted, the keys of the first hash are used. Empty input

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: philiprehberger-csv_kit
 version: !ruby/object:Gem::Version
-  version: 0.8.0
+  version: 0.10.0
 platform: ruby
 authors:
 - Philip Rehberger
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2026-04-17 00:00:00.000000000 Z
+date: 2026-05-07 00:00:00.000000000 Z
 dependencies: []
 description: Streaming CSV processor with row-by-row transforms, validations, column
   plucking, streaming each_hash iteration, filtering, writing, error recovery, and