pi-lens/rules/tree-sitter-queries/python/open-invalid-mode.yml

Real-time code feedback for pi — LSP, linters, formatters, type-checking, structural analysis & booboo

# Invalid Open Mode
# Detects calls to open() with invalid mode strings
id: open-invalid-mode
name: Invalid Open Mode
severity: error
category: reliability
defect_class: correctness
inline_tier: blocking
language: python

message: "open() called with invalid mode '{{MODE}}'"

description: |
  Python's open() builtin accepts mode from a limited set:
  r, w, a, x (basic modes), optionally combined with b/t/+ suffix.
  Invalid mode strings raise ValueError at runtime.

  Detection: matches strings of length ≥ 2 where the string contains
  a character NOT in {r, w, a, x, b, t, +}. This catches typos like
  "rwb", "rrr", "qq", and outright garbage like "xyz".

  The known limitation: this regex doesn't catch semantically-invalid
  combinations that use only valid chars (e.g. "rw" — should be "r+").
  Full validation requires an enum lookup.

  ✅ FIX: Use a valid mode string like 'r', 'w', 'rb', 'r+'

query: |
  (call
    function: (identifier) @FUNC
    arguments: (argument_list
      (_)
      (string) @MODE)
    (#eq? @FUNC "open"))

metavars:
  - FUNC
  - MODE

post_filter: open_mode_invalid

has_fix: false

tags:
  - reliability
  - python-specific
  - builtin

examples:
  bad: |
    f = open("file.txt", "rwb")  # ValueError: invalid mode (contains b but invalid combo)
    f = open("file.txt", "rrr")  # ValueError: invalid mode (duplicate)
    f = open("file.txt", "qq")   # ValueError: invalid mode (bad chars)
  
  good: |
    f = open("file.txt", "r")    # OK
    f = open("file.txt", "rb+")  # OK
    f = open("file.txt", "w")    # OK