From 2e2512ab52e19c735d825cc64121536311c229a4 Mon Sep 17 00:00:00 2001
From: Mike Bloy <mike@bloy.org>
Date: Fri, 24 Nov 2023 11:57:24 -0600
Subject: [PATCH] ex 5.1

---
 reader.py         | 123 +++++++++++++++-------------------------------
 reader_classes.py |  87 ++++++++++++++++++++++++++++++++
 2 files changed, 127 insertions(+), 83 deletions(-)
 create mode 100644 reader_classes.py

diff --git a/reader.py b/reader.py
index e33048a..b20ed33 100644
--- a/reader.py
+++ b/reader.py
@@ -1,87 +1,44 @@
-import collections.abc
 import csv
-from abc import ABC, abstractmethod
+from typing import Iterable, Optional, Sequence
 
 
-class DataCollection(collections.abc.Sequence):
-    def __init__(self, headers):
-        self.headers = headers
-        self.data = dict()
-        for name in headers:
-            self.data[name] = []
-
-    def __len__(self):
-        return len(self.data[self.headers[0]])
-
-    def __getitem__(self, index):
-        if isinstance(index, slice):
-            value = DataCollection(self.headers)
-        else:
-            value = {}
-
-        for name in self.headers:
-            if isinstance(index, slice):
-                value.data[name] = self.data[name][index]
-            else:
-                value[name] = self.data[name][index]
-        return value
-
-    def append(self, d):
-        for name in self.headers:
-            self.data[name].append(d[name])
-
-
-class CSVParser(ABC):
-    def parse(self, filename):
-        records = []
-        with open(filename) as f:
-            rows = csv.reader(f)
-            headers = next(rows)
-            for row in rows:
-                records.append(self.make_record(headers, row))
-        return records
-
-    @abstractmethod
-    def make_record(self, headers, row):
-        pass
-
-
-class DictCSVParser(CSVParser):
-    def __init__(self, types):
-        self.types = types
-
-    def make_record(self, headers, row):
-        return {name: func(val) for name, func, val in zip(headers, self.types, row)}
-
-
-class InstanceCSVParser(CSVParser):
-    def __init__(self, cl):
-        self.cls = cl
-
-    def make_record(self, headers, row):
-        return self.cls.from_row(row)
-
-
-def read_csv_as_dicts(filename, conversions):
-    parser = DictCSVParser(conversions)
-    records = parser.parse(filename)
-    return records
-
-
-def read_csv_as_instances(filename, cls):
-    """Read a CSV file into a list of instances"""
-    parser = InstanceCSVParser(cls)
-    records = parser.parse(filename)
-    return records
-
-
-def read_csv_as_columns(filename, conversions):
-    with open(filename) as f:
-        rows = csv.reader(f)
+def csv_as_dicts(
+    lines: Iterable[str], types: Sequence[type], headers: Optional[Sequence[str]] = None
+):
+    records = []
+    rows = csv.reader(lines)
+    if headers is None:
         headers = next(rows)
-        value = DataCollection(headers)
-        for row in rows:
-            value.append(
-                {name: func(val) for name, func, val in zip(headers, conversions, row)}
-            )
-    return value
+    for row in rows:
+        record = {name: func(val) for name, func, val in zip(headers, types, row)}
+        records.append(record)
+    return records
+
+
+def read_csv_as_dicts(
+    filename: str, types: Sequence[type], headers: Optional[Sequence[str]] = None
+):
+    """
+    Read CSV data into list of dictionaries with optional type conversion.
+    """
+    with open(filename) as file:
+        return csv_as_dicts(file, types, headers)
+
+
+def csv_as_instances(lines: Iterable[str], cls: type, has_headers: bool = True):
+    records = []
+    rows = csv.reader(lines)
+    if has_headers:
+        next(rows)
+    for row in rows:
+        record = cls.from_row(row)
+        records.append(record)
+    return records
+
+
+def read_csv_as_instances(filename: str, cls: type, has_headers: bool = True):
+    """
+    Read CSV data into list of instances.
+    """
+    with open(filename) as file:
+        return csv_as_instances(file, cls, has_headers)
diff --git a/reader_classes.py b/reader_classes.py
new file mode 100644
index 0000000..e33048a
--- /dev/null
+++ b/reader_classes.py
@@ -0,0 +1,87 @@
+import collections.abc
+import csv
+from abc import ABC, abstractmethod
+
+
+class DataCollection(collections.abc.Sequence):
+    def __init__(self, headers):
+        self.headers = headers
+        self.data = dict()
+        for name in headers:
+            self.data[name] = []
+
+    def __len__(self):
+        return len(self.data[self.headers[0]])
+
+    def __getitem__(self, index):
+        if isinstance(index, slice):
+            value = DataCollection(self.headers)
+        else:
+            value = {}
+
+        for name in self.headers:
+            if isinstance(index, slice):
+                value.data[name] = self.data[name][index]
+            else:
+                value[name] = self.data[name][index]
+        return value
+
+    def append(self, d):
+        for name in self.headers:
+            self.data[name].append(d[name])
+
+
+class CSVParser(ABC):
+    def parse(self, filename):
+        records = []
+        with open(filename) as f:
+            rows = csv.reader(f)
+            headers = next(rows)
+            for row in rows:
+                records.append(self.make_record(headers, row))
+        return records
+
+    @abstractmethod
+    def make_record(self, headers, row):
+        pass
+
+
+class DictCSVParser(CSVParser):
+    def __init__(self, types):
+        self.types = types
+
+    def make_record(self, headers, row):
+        return {name: func(val) for name, func, val in zip(headers, self.types, row)}
+
+
+class InstanceCSVParser(CSVParser):
+    def __init__(self, cl):
+        self.cls = cl
+
+    def make_record(self, headers, row):
+        return self.cls.from_row(row)
+
+
+def read_csv_as_dicts(filename, conversions):
+    parser = DictCSVParser(conversions)
+    records = parser.parse(filename)
+    return records
+
+
+def read_csv_as_instances(filename, cls):
+    """Read a CSV file into a list of instances"""
+    parser = InstanceCSVParser(cls)
+    records = parser.parse(filename)
+    return records
+
+
+def read_csv_as_columns(filename, conversions):
+    with open(filename) as f:
+        rows = csv.reader(f)
+        headers = next(rows)
+        value = DataCollection(headers)
+        for row in rows:
+            value.append(
+                {name: func(val) for name, func, val in zip(headers, conversions, row)}
+            )
+    return value