From 5cf382d0e0c4e371c221cb7562551e5bc87a9c7b Mon Sep 17 00:00:00 2001
From: Filipe Fernandes <ocefpaf@gmail.com>
Date: Thu, 7 May 2026 15:39:47 -0300
Subject: [PATCH 1/2] update

---
 .pre-commit-config.yaml | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
index 6710cea..206c29c 100644
--- a/.pre-commit-config.yaml
+++ b/.pre-commit-config.yaml
@@ -39,7 +39,7 @@ repos:
     - id: add-trailing-comma
 
 - repo: https://github.com/astral-sh/ruff-pre-commit
-  rev: v0.15.9
+  rev: v0.15.12
   hooks:
     - id: ruff
       args: ["--fix", "--show-fixes"]
@@ -62,12 +62,12 @@ repos:
     - id: nb-strip-paths
 
 - repo: https://github.com/tox-dev/pyproject-fmt
-  rev: v2.21.0
+  rev: v2.21.2
   hooks:
     - id: pyproject-fmt
 
 - repo: https://github.com/woodruffw/zizmor-pre-commit
-  rev: v1.23.1
+  rev: v1.24.1
   hooks:
     - id: zizmor
 

From 7b2b87e34eb6334035496ceb901f271f5c33b8d0 Mon Sep 17 00:00:00 2001
From: Filipe Fernandes <ocefpaf@gmail.com>
Date: Thu, 7 May 2026 15:39:52 -0300
Subject: [PATCH 2/2] coerce bad num values, pin chardet, fail early

---
 ctd/read.py      | 44 ++++++++++++++++++++++----------------------
 requirements.txt |  2 +-
 2 files changed, 23 insertions(+), 23 deletions(-)

diff --git a/ctd/read.py b/ctd/read.py
index a9c213e..34b48da 100644
--- a/ctd/read.py
+++ b/ctd/read.py
@@ -86,6 +86,8 @@ def _read_file(fname: str | Path | StringIO) -> StringIO:
         )
     # Read as bytes but we need to return strings for the parsers.
     encoding = chardet.detect(contents)["encoding"]
+    if encoding is None:
+        encoding = "utf-8"
     text = contents.decode(encoding=encoding, errors="replace")
     return StringIO(text)
 
@@ -418,17 +420,28 @@ def from_cnv(fname: str | Path) -> pd.DataFrame:
     metadata = _parse_seabird(f.readlines(), ftype="cnv")
 
     f.seek(0)
-    cast = pd.read_fwf(
-        f,
-        header=None,
-        index_col=None,
-        names=metadata["names"],
-        skiprows=metadata["skiprows"],
-        sep=r"\s+",
-        widths=[11] * len(metadata["names"]),
-    )
+    lines = f.readlines()[metadata["skiprows"] :]
     f.close()
 
+    data = [line.strip().split() for line in lines]
+    cast = pd.DataFrame(
+        data,
+        columns=metadata["names"],
+    )
+
+    dtypes = {"bpos": int, "pumps": bool, "flag": bool}
+    for column in cast.columns:
+        if column in dtypes:
+            cast[column] = cast[column].astype(dtypes[column])
+        else:
+            try:
+                cast[column] = pd.to_numeric(cast[column], errors="coerce")
+            except ValueError:
+                warnings.warn(
+                    f"Could not convert {column} to float.",
+                    stacklevel=2,
+                )
+
     prkeys = [
         "prM",
         "prE",
@@ -476,19 +489,6 @@ def from_cnv(fname: str | Path) -> pd.DataFrame:
         name = _basename(fname)[1]
         metadata["name"] = str(name)
 
-    dtypes = {"bpos": int, "pumps": bool, "flag": bool}
-    for column in cast.columns:
-        if column in dtypes:
-            cast[column] = cast[column].astype(dtypes[column])
-        else:
-            try:
-                cast[column] = cast[column].astype(float)
-            except ValueError:
-                warnings.warn(
-                    f"Could not convert {column} to float.",
-                    stacklevel=2,
-                )
-
     cast._metadata = metadata  # noqa: SLF001
     return cast
 
diff --git a/requirements.txt b/requirements.txt
index a8cf98b..e2f463d 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -1,4 +1,4 @@
-chardet
+chardet<7
 gsw>=3.3.0
 matplotlib
 numpy>=2