Introduce check for special characters

.github/workflows/frontend-linting.yml

@@ -30,4 +30,7 @@ jobs:
 
       - name: Run linting
         working-directory: frontend
-        run: npm run lint
+        run: npm run lint
+
+      - name: Check for forbidden Unicode characters
+        run: bash backend/ci/forbidden_chars_check.sh frontend/ --ext .ts .tsx .js .jsx .json .html .css

.github/workflows/linting.yml

@@ -27,4 +27,7 @@ jobs:
         run: ruff format --check backend/
 
       - name: Check linting with ruff
-        run: ruff check backend/
+        run: ruff check backend/
+
+      - name: Check for forbidden Unicode characters
+        run: bash backend/ci/forbidden_chars_check.sh backend/ docs/ --ext .py .rst

backend/ci/forbidden_chars_check.sh

@@ -0,0 +1,152 @@
+#!/usr/bin/env bash
+set -uo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+
+CHARS=(
+    $'\u2013' $'\u2014' $'\u2212' $'\u2018' $'\u2019'
+    $'\u201C' $'\u201D' $'\u2026' $'\u00A0' $'\u200B'
+    $'\u200C' $'\u200D' $'\u2060' $'\uFEFF' $'\u00AD'
+    $'\u2022' $'\u00D7' $'\u00F7' $'\u2190' $'\u2192'
+    $'\u21D2' $'\u2260' $'\u2264' $'\u2265'
+)
+
+DESCS=(
+    "EN DASH (–)"
+    "EM DASH (—)"
+    "UNICODE MINUS (−)"
+    "LEFT SINGLE QUOTATION MARK (‘)"
+    "RIGHT SINGLE QUOTATION MARK (’)"
+    "LEFT DOUBLE QUOTATION MARK (“)"
+    "RIGHT DOUBLE QUOTATION MARK (”)"
+    "HORIZONTAL ELLIPSIS (…)"
+    "NON-BREAKING SPACE (NBSP)"
+    "ZERO WIDTH SPACE"
+    "ZERO WIDTH NON-JOINER"
+    "ZERO WIDTH JOINER"
+    "WORD JOINER"
+    "ZERO WIDTH NO-BREAK SPACE (BOM)"
+    "SOFT HYPHEN"
+    "BULLET (•)"
+    "MULTIPLICATION SIGN (×)"
+    "DIVISION SIGN (÷)"
+    "LEFT ARROW (←)"
+    "RIGHT ARROW (→)"
+    "RIGHTWARDS DOUBLE ARROW (⇒)"
+    "NOT EQUAL TO (≠)"
+    "LESS-THAN OR EQUAL TO (≤)"
+    "GREATER-THAN OR EQUAL TO (≥)"
+)
+
+EXCLUDED_DIRS=(
+    __pycache__ .pytest_cache .mypy_cache .ruff_cache
+    .tox .venv venv ibex_venv imaspy_venv imas_core_develop_venv
+    build dist node_modules .git .webpack out ci generated _build
+)
+
+DIRS=()
+EXTS=()
+AFTER_EXT=false
+
+for arg in "$@"; do
+    if [ "$arg" = "--help" ] || [ "$arg" = "-h" ]; then
+        echo "Usage: $(basename "$0") [directories...] [--ext extensions...]"
+        echo ""
+        echo "Scan source files for forbidden Unicode characters."
+        echo ""
+        echo "Arguments:"
+        echo "  directories    One or more directories to scan (default: ../ and ../../frontend)"
+        echo "  --ext          File extensions to check (default: all files)"
+        echo ""
+        echo "Examples:"
+        echo "  $(basename "$0")                                          Scan backend/ and frontend/"
+        echo "  $(basename "$0") backend/ --ext .py                       Scan only .py files in backend/"
+        echo "  $(basename "$0") frontend/ --ext .ts .tsx .js             Scan only TS/JS files in frontend/"
+        echo "  $(basename "$0") src/ docs/ --ext .py .md                 Scan custom dirs with custom extensions"
+        exit 0
+    elif [ "$arg" = "--ext" ]; then
+        AFTER_EXT=true
+    elif [ "$AFTER_EXT" = true ]; then
+        EXTS+=("$arg")
+    else
+        DIRS+=("$arg")
+    fi
+done
+
+# checks for forbidden chars in ../. (backend), ../../docs, and ../../frontend by default
+# if no --ext given, all files are checked
+if [ ${#DIRS[@]} -eq 0 ]; then
+    DIRS=("$SCRIPT_DIR/../" "$SCRIPT_DIR/../../docs" "$SCRIPT_DIR/../../frontend")
+fi
+
+find_args=()
+
+for dir in "${DIRS[@]}"; do
+    if [ ! -d "$dir" ]; then
+        echo "Directory not found: $dir" >&2
+        exit 1
+    fi
+
+    find_args+=("$(cd "$dir" && pwd)")
+done
+
+find_args=("${find_args[@]}" -type f)
+
+if [ ${#EXTS[@]} -gt 0 ]; then
+    find_args+=("(")
+    find_args+=(-name "*${EXTS[0]}")
+    for ((i=1; i<${#EXTS[@]}; i++)); do
+        find_args+=(-o -name "*${EXTS[i]}")
+    done
+    find_args+=(")")
+fi
+
+for d in "${EXCLUDED_DIRS[@]}"; do
+    find_args+=(! -path "*/$d/*")
+done
+
+# Collect all matching files
+all_files=()
+while IFS= read -r -d '' file; do
+    all_files+=("$file")
+done < <(find "${find_args[@]}" -print0 2>/dev/null)
+
+file_count=${#all_files[@]}
+
+if [ "$file_count" -eq 0 ]; then
+    echo "No files to check."
+    exit 0
+fi
+
+echo "Checking $file_count files..."
+
+errors=0
+
+for ((i=0; i<${#CHARS[@]}; i++)); do
+    char="${CHARS[i]}"
+    desc="${DESCS[i]}"
+
+    matches=$(printf '%s\0' "${all_files[@]}" | xargs -0 grep -In "$char" 2>/dev/null) || true
+    if [ -n "$matches" ]; then
+        while IFS= read -r grep_line; do
+            file="${grep_line%%:*}"
+            rest="${grep_line#*:}"
+            lineno="${rest%%:*}"
+            content="${rest#*:}"
+
+            prefix="${content%%$char*}"
+            col=$(( ${#prefix} + 1 ))
+
+            echo "$file:$lineno:$col: $desc"
+        done <<< "$matches"
+        ((errors++)) || true
+    fi
+done
+
+if [ "$errors" -gt 0 ]; then
+    echo ""
+    echo "❌ Forbidden Unicode characters found in $errors file(s)."
+    exit 1
+fi
+
+echo "✅ No forbidden Unicode characters found."

docs/source/conf.py

@@ -26,7 +26,7 @@
 
 
 # -- Project information -----------------------------------------------------
-# The documented project’s name
+# The documented project's name
 project = src_project = PROJECT = "ibex"
 PACKAGE = "ibex"
 src_group = GROUP = "IMEX"

docs/source/developers_manual/backend_development/backend_development_introduction.rst

@@ -9,9 +9,9 @@ Backend structure
 
 The IBEX backend is structured into three distinct layers, each represented by a corresponding directory within the ibex Python package:
 
-* endpoints – Defines all HTTP API endpoints. This layer is strictly limited to request handling and routing, and does not contain any business logic.
-* core – Serves as an abstraction layer between the endpoints and data_sources layers. Its primary role is to decouple application logic from specific data source implementations, enabling interchangeability. May include minimal logic when necessary.
-* data_sources – Implements the core application logic. This layer is responsible for all communication with data sources (IMAS-Python) and constructs the JSON responses returned to frontend.
+* endpoints - Defines all HTTP API endpoints. This layer is strictly limited to request handling and routing, and does not contain any business logic.
+* core - Serves as an abstraction layer between the endpoints and data_sources layers. Its primary role is to decouple application logic from specific data source implementations, enabling interchangeability. May include minimal logic when necessary.
+* data_sources - Implements the core application logic. This layer is responsible for all communication with data sources (IMAS-Python) and constructs the JSON responses returned to frontend.
 
 Endpoints discovering and testing
 -----------------------------------

docs/source/index.rst

@@ -7,7 +7,7 @@ Ibex Manual
 =============
 
 IBEX is a web-based application designed for efficient traversal and visualization of data stored in the Integrated Data Structure (IDS).
-The application follows a client–server architecture, consisting of a frontend for interactive data exploration and a backend responsible for
+The application follows a client-server architecture, consisting of a frontend for interactive data exploration and a backend responsible for
 data processing and communication with data sources. The backend leverages the `IMAS Python <https://github.com/iterorganization/IMAS-Python>`_ to access, parse, and manipulate IDS data,
 enabling seamless integration with existing IMAS-compatible databases.
 IBEX features a modular and extensible architecture, with the IMAS Python API encapsulated as a replaceable component, allowing it to be substituted with an alternative data access layer if needed.