ga4-export-fixer 0.9.0-dev.1 → 0.9.0-dev.11

package/README.md

@@ -198,7 +198,8 @@ Create a new **ga4_events_enhanced** table using a **.js** file in your reposito
 const { ga4EventsEnhanced } = require('ga4-export-fixer');
 
 const config = {
-  sourceTable: constants.GA4_TABLES.MY_GA4_EXPORT
+  // using hard-coded GA4 export path
+  sourceTable: '`project.analytics_12345.events_*`'
 };
 
 ga4EventsEnhanced.createTable(publish, config);
@@ -212,6 +213,7 @@ ga4EventsEnhanced.createTable(publish, config);
 const { ga4EventsEnhanced } = require('ga4-export-fixer');
 
 const config = {
+  // GA4 export path declared, using the table reference object
   sourceTable: constants.GA4_TABLES.MY_GA4_EXPORT,
   // use dataformTableConfig to make changes to the default Dataform table configuration
   dataformTableConfig: {
@@ -290,7 +292,8 @@ js {
   const { ga4EventsEnhanced } = require('ga4-export-fixer');
 
   const config = {
-    sourceTable: ref(constants.GA4_TABLES.MY_GA4_EXPORT),
+    // using hard-coded GA4 export path
+    sourceTable: '`project.analytics_12345.events_*`',
     self: self(),
     incremental: incremental()
   };
@@ -314,7 +317,7 @@ All fields are optional except `sourceTable`. Default values are applied automat
 
 | Field                  | Type                    | Default/Required                   | Description                                                                                                                                                                                                                                                                                                                  |
 | ---------------------- | ----------------------- | ---------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| `sourceTable`          | Dataform ref() / string | **required**                       | Source GA4 export table. Use `ref()` in Dataform or a string in format ``project.dataset.table``                                                                                                                                                                                                                             |
+| `sourceTable`          | Dataform ref / object / string | **required**                       | Source GA4 export table. Inside an SQLX `js { }` block use `ref(...)`. From a `.js` definition file use a `{ schema, name }` ref object (resolved later via `ctx.ref()`) or a backtick-quoted ``` `project.dataset.events_*` ``` string for an external table. |
 | `self`                 | Dataform self()         | **required for .SQLX deployment**  | Reference to the table itself. Use `self()` in Dataform                                                                                                                                                                                                                                                                      |
 | `incremental`          | Dataform incremental()  | **required for .SQLX deployment**  | Switch between incremental and full refresh logic. Use `incremental()` in Dataform                                                                                                                                                                                                                                           |
 | `dataformTableConfig`  | object                  | **In JS deployment only.** [See default](#default-dataformtableconfig) | Override the default Dataform table configuration for JS deployment. See: [ITableConfig reference](https://docs.cloud.google.com/dataform/docs/reference/dataform-core-reference#itableconfig) |
@@ -334,6 +337,7 @@ All fields are optional except `sourceTable`. Default values are applied automat
 | `preOperations`        | object                  | [See details](#preOperations)       | Date range and incremental refresh configuration                                                                                                                                                                                                                                                                             |
 | `eventParamsToColumns` | object[]                | `[]`                                | Event parameters to promote to columns. [See item schema](#eventParamsToColumns)                                                                                                                                                                                                                                             |
 | `customSteps`          | object[]                | `[]`                                | User-defined CTEs appended to the pipeline after `enhanced_events`. [See Custom CTEs](#custom-ctes)                                                                                                                                                                                                                          |
+| `enrichments`          | object[]                | `[]`                                | Declarative external-data enrichments joined into `enhanced_events`. [See Data Enrichments](#data-enrichments)                                                                                                                                                                                                               |
 
 <a id="default-dataformtableconfig"></a>
 <details>
@@ -473,7 +477,8 @@ itemListAttribution: { lookbackType: 'TIME', lookbackTimeMs: 86400000 }
 | `session_data`           | yes                                   | Session-level aggregations (grouped by `session_id`).                                                                                                |
 | `items_unnested`         | only when `itemListAttribution` is on | Per-event item rows (one row per item per ecommerce event), with attribution window function applied.                                                |
 | `items_rebuilt`          | only when `itemListAttribution` is on | Re-aggregated items with attributed list fields, joined back to events via `_item_row_id`.                                                           |
-| `enhanced_events`        | yes                                   | The package's standard output shape (joined event_data + session_data + items_rebuilt, columns ordered, incremental date filter applied). The natural starting point for most custom CTEs. |
+| `enrich_<name>`          | only when configured via `enrichments` | One CTE per [enrichment](#data-enrichments) entry, providing dim data for joining into `enhanced_events`.                                              |
+| `enhanced_events`        | yes                                   | The package's standard output shape (joined event_data + session_data + items_rebuilt + enrich_*, columns ordered, incremental date filter applied). The natural starting point for most custom CTEs. |
 
 Example custom step using the raw SQL format:
 
@@ -521,6 +526,93 @@ end`,
 
 > **Note:** Built-in assertions assume the package's standard schema. If your custom CTEs rename, drop, or filter rows in ways that break those assumptions, disable the affected assertions explicitly via the `assertions` config option.
 
+<a id="data-enrichments"></a>
+
+**`enrichments`** — declaratively join external dimension data into `enhanced_events` (cohort labels, page metadata, marketing attribution, etc.). Each entry describes one dim source plus the join — the package generates the source CTE, the `LEFT JOIN`, and column descriptions automatically.
+
+For typical use cases this is the right tool; reach for `customSteps` only when you need a transformation that doesn't fit a flat dim join.
+
+**Per-enrichment shape:**
+
+| Field | Type | Required | Description |
+| --- | --- | --- | --- |
+| `name` | string | Yes | Used in the generated `enrich_<name>` CTE name. Unique within `enrichments`. |
+| `level` | `'event'` / `'item'` | No, defaults to `'event'` | Join grain. `'event'` joins external dim data onto each event row (any column on `enhanced_events` as the key). `'item'` joins external dim data onto each item inside the `items` array (any field on the items struct or any event_data column as the key). |
+| `source` | Dataform ref / object / string | Yes | Source dim table. Inside an SQLX `js { }` block use `ref(...)`. From a `.js` definition file use a `{ schema, name }` ref object (resolved later via `ctx.ref()`) or a backtick-quoted ``` `project.dataset.table` ``` string for an external table. |
+| `joinKey` | string / string[] | Yes | For `level: 'event'`: column name(s) on `enhanced_events`. For `level: 'item'`: field name(s) on the items struct (e.g. `'item_id'`) or column name(s) on `event_data` (e.g. `'user_pseudo_id'`). Composite keys (array) compile to `USING(col1, col2, ...)`. |
+| `columns` | string[] | Yes | Source columns to add to the output (excluding `joinKey`). Names matching existing columns are coalesced with the original (`coalesce(enrich.col, original)`) so missed JOINs fall back to the existing value. |
+| `dedupe` | boolean | No, defaults to `false` | When `true`, wraps the source CTE in `qualify row_number() over (partition by <joinKey>) = 1` for non-unique-key dim sources. Non-deterministic which row wins; for strict needs, pre-aggregate in source SQL. |
+
+**Coalesce-or-add semantics.** If an enrichment column name matches an existing column on `enhanced_events` (a column promoted via `eventParamsToColumns`, a package-generated column, or a default GA4 column from the export), the enrichment value is coalesced with the original: `coalesce(enrich_<name>.<col>, <original>) as <col>`. Rows where the JOIN matches get the enrichment value; rows where it misses fall back to the existing value rather than going NULL. If there is no overlap, the column is added as a plain `enrich_<name>.<col>`.
+
+**Example** — attach user cohort labels by `user_pseudo_id` (Dataform-declared table referenced by `{ schema, name }`):
+
+```javascript
+enrichments: [
+    {
+        name: 'cohorts',
+        level: 'event',
+        source: { schema: 'analytics', name: 'user_cohorts' },
+        joinKey: 'user_pseudo_id',
+        columns: ['cohort_label', 'lifecycle_stage'],
+    },
+],
+```
+
+**Example** — composite key (date + user) for daily-varying dim data, with dedupe safety net (external table referenced by backtick-FQN):
+
+```javascript
+enrichments: [
+    {
+        name: 'segments',
+        level: 'event',
+        source: '`my-project.analytics.daily_user_segments`',
+        joinKey: ['event_date', 'user_pseudo_id'],
+        columns: ['segment'],
+        dedupe: true,
+    },
+],
+```
+
+**Example** — fix a promoted event parameter via enrichment (coalesce case: enrichment value wins where the JOIN matches, original kept where it doesn't):
+
+```javascript
+{
+    eventParamsToColumns: [{ name: 'page_title', type: 'string' }],
+    enrichments: [
+        {
+            name: 'titles',
+            level: 'event',
+            source: { schema: 'analytics', name: 'page_title_overrides' },
+            joinKey: 'page_location',
+            columns: ['page_title'],   // overlaps the promoted column → coalesce(enrich.page_title, event_data.page_title)
+        },
+    ],
+}
+```
+
+**Example** — item-level enrichment: attach product master data to each item via `item_id`. The enrichment flows into the `items` array struct; `margin_bucket` is added as a new item-struct field, and `item_category` overlap-coalesces against the original. Item-level enrichment columns do NOT appear at the event grain — they live inside `items[].<col>`:
+
+```javascript
+enrichments: [
+    {
+        name: 'products',
+        level: 'item',
+        source: { schema: 'analytics', name: 'product_master' },
+        joinKey: 'item_id',                                  // joins on item.item_id
+        columns: ['margin_bucket', 'item_category'],         // margin_bucket is additive; item_category overlap-coalesces
+    },
+],
+```
+
+For `level: 'item'`, valid `joinKey` values are any field on the GA4 items struct (`item_id`, `item_category`, etc.) or any column on `event_data` (`user_pseudo_id`, `event_date`, etc.). An event-level and an item-level enrichment may share the same column name (e.g. both writing `cohort`) — the two columns target structurally distinct slots (`enhanced_events.cohort` at event grain vs `items[].cohort` inside the items array) and are not in collision.
+
+> **Note:** Each enrichment generates a CTE named `enrich_<name>` at the top of the pipeline. The `enrich_*` namespace is part of the reserved-names contract — `customSteps` cannot use these names. The active reserved set includes only the names of enrichments actually configured.
+
+> **Note:** Event-level enrichment columns get auto-generated descriptions (`Added by enrichment '<name>' (joined on <joinKey> from <source>).` for new columns; `Coalesced by enrichment '<name>' (...; falls back to original on missed JOIN). Original: <description>` for overlapping columns). User-supplied `dataformTableConfig.columns` overrides win — the auto-generated description is the default. Item-level enrichment columns do not receive auto-generated descriptions (BigQuery does not surface per-field descriptions on STRUCT-array fields cleanly through Dataform's column-description mechanism).
+
+> **Note:** `joinKey` and `columns` entries must be plain SQL identifiers — inline aliases like `'id as user_id'` are rejected at validation time. If your dim source uses a different column name, alias it in an upstream Dataform view and point `source` at that view.
+
 <br>
 
 ---

package/documentation.js

@@ -1,223 +1,272 @@
-const constants = require('./constants');
-const { version } = require('./package.json');
-
-/**
- * Composes a multi-section column description string from individual sections.
- * Sections with null/undefined/empty values are omitted.
- * Sections are separated by line breaks for readability.
- *
- * @param {Object} sections - { base, lineage, typicalUse, config }
- * @returns {string} Composed description
- */
-const composeDescription = (sections) => {
-    const parts = [];
-
-    if (sections.base) {
-        parts.push(sections.base);
-    }
-
-    if (sections.lineage) {
-        parts.push(`Lineage: ${sections.lineage}`);
-    }
-
-    if (sections.typicalUse) {
-        parts.push(`Typical use: ${sections.typicalUse}`);
-    }
-
-    if (sections.config) {
-        parts.push(`Config: ${sections.config}`);
-    }
-
-    return parts.join('\n\n');
-};
-
-/**
- * Returns a formatted lineage text string for a column, or null if no lineage data exists.
- *
- * @param {string} columnName - The column name to look up.
- * @param {Object} columnLineage - The lineage data object mapping column names to { source, note }.
- * @returns {string|null} Formatted lineage string, e.g. "Derived -- Concatenation of ..."
- */
-const getLineageText = (columnName, columnLineage) => {
-    const entry = columnLineage[columnName];
-    if (!entry) return null;
-
-    const sourceLabels = {
-        'ga4_export': 'Standard GA4 export field',
-        'ga4_export_modified': 'GA4 export field (modified)',
-        'derived': 'Derived',
-    };
-
-    const label = sourceLabels[entry.source] || entry.source;
-    return entry.note ? `${label} -- ${entry.note}` : label;
-};
-
-/**
- * Builds a map of config-specific notes for columns based on the provided configuration.
- * Extracts the configuration-dependent description suffixes into a { columnName: "note" } map.
- *
- * @param {Object} config - The merged configuration object.
- * @returns {Object} Map of column names to config note strings.
- */
-const buildConfigNotes = (config) => {
-    const notes = {};
-
-    if (!config) return notes;
-
-    const append = (key, text) => {
-        notes[key] = notes[key] ? `${notes[key]}. ${text}` : text;
-    };
-
-    // timezone
-    if (config.timezone) {
-        append('event_datetime', `Timezone: ${config.timezone}`);
-    }
-
-    // customTimestampParam
-    if (config.customTimestampParam) {
-        append('event_datetime', `Custom timestamp parameter: '${config.customTimestampParam}'`);
-        append('event_custom_timestamp', `Source parameter: '${config.customTimestampParam}'`);
-    }
-
-    // data_is_final
-    if (config.dataIsFinal) {
-        const method = config.dataIsFinal.detectionMethod;
-        if (method === 'DAY_THRESHOLD') {
-            append('data_is_final', `Detection method: DAY_THRESHOLD (${config.dataIsFinal.dayThreshold} days)`);
-        } else {
-            append('data_is_final', `Detection method: EXPORT_TYPE`);
-        }
-    }
-
-    // excludedEvents
-    if (config.excludedEvents && config.excludedEvents.length > 0) {
-        append('event_name', `Excluded events: ${config.excludedEvents.join(', ')}`);
-    }
-
-    // excludedEventParams
-    if (config.excludedEventParams && config.excludedEventParams.length > 0) {
-        append('event_params', `Excluded parameters: ${config.excludedEventParams.join(', ')}`);
-    }
-
-    // sessionParams
-    if (config.sessionParams && config.sessionParams.length > 0) {
-        append('session_params', `Configured parameters: ${config.sessionParams.join(', ')}`);
-    }
-
-    // includedExportTypes
-    if (config.includedExportTypes) {
-        const types = Object.entries(config.includedExportTypes)
-            .filter(([, enabled]) => enabled)
-            .map(([type]) => type);
-        if (types.length > 0) {
-            append('export_type', `Included export types: ${types.join(', ')}`);
-        }
-    }
-
-    return notes;
-};
-
-/**
- * Returns a deep copy of the column descriptions, enriched with
- * lineage, typical use, and configuration-specific sections composed into
- * multi-section descriptions.
- *
- * @param {Object} config - The merged configuration object.
- * @param {Object} columnMetadata - Column metadata provided by the table module.
- * @param {Object} columnMetadata.descriptions - Column descriptions (Dataform ITableConfig columns format).
- * @param {Object} columnMetadata.lineage - Column lineage data mapping column names to { source, note }.
- * @param {Object} columnMetadata.typicalUse - Column typical use mapping column names to description strings.
- * @returns {Object} Column descriptions object in Dataform ITableConfig columns format.
- */
-const getColumnDescriptions = (config, columnMetadata) => {
-    const descriptions = JSON.parse(JSON.stringify(columnMetadata.descriptions));
-
-    const configNotes = buildConfigNotes(config);
-
-    // Compose multi-section descriptions for each top-level column
-    for (const key of Object.keys(descriptions)) {
-        const isStruct = typeof descriptions[key] === 'object' && descriptions[key].description;
-        const baseDesc = isStruct ? descriptions[key].description : (typeof descriptions[key] === 'string' ? descriptions[key] : null);
-
-        if (!baseDesc) continue;
-
-        const composed = composeDescription({
-            base: baseDesc,
-            lineage: getLineageText(key, columnMetadata.lineage),
-            typicalUse: columnMetadata.typicalUse[key] || null,
-            config: configNotes[key] || null,
-        });
-
-        if (isStruct) {
-            descriptions[key].description = composed;
-        } else {
-            descriptions[key] = composed;
-        }
-    }
-
-    // Add descriptions for dynamically promoted event parameter columns
-    if (config && config.eventParamsToColumns && config.eventParamsToColumns.length > 0) {
-        config.eventParamsToColumns.forEach(p => {
-            const columnName = p.columnName || p.name;
-            const type = p.type ? ` (${p.type})` : ' (any data type)';
-            descriptions[columnName] = composeDescription({
-                base: `Promoted from event parameter '${p.name}'${type}`,
-                lineage: `Derived -- Promoted from the event_params array`,
-                typicalUse: 'Promoted event parameter available as a top-level column for direct filtering and aggregation',
-                config: null,
-            });
-        });
-    }
-
-    return descriptions;
-};
-
-/**
- * Checks whether a column (or its parent struct) is excluded by the config.
- *
- * @param {string[]} dependsOn - Column names this entry depends on.
- * @param {string[]} excludedColumns - Combined excluded columns from config.
- * @returns {boolean} True if ALL dependsOn columns are excluded.
- */
-const isExcluded = (dependsOn, excludedColumns) => {
-    if (!dependsOn || dependsOn.length === 0) return false;
-    return dependsOn.every(col => excludedColumns.includes(col));
-};
-
-/**
- * Builds the full table description by combining table-specific sections
- * with shared sections (package attribution, config JSON dump).
- *
- * @param {Object} config - The merged configuration object.
- * @param {string[]} tableSections - Table-specific description sections (provided by the table module).
- * @returns {string} The composed table description.
- */
-const buildTableDescription = (config, tableSections) => {
-    const sections = [...tableSections];
-
-    // Package Attribution
-    sections.push(`${constants.TABLE_DESCRIPTION_SUFFIX} Version: ${version}\n${constants.TABLE_DESCRIPTION_DOCUMENTATION_LINK}`);
-
-    // Config JSON dump
-    const configForDump = Object.fromEntries(
-        Object.entries(config).filter(([key]) => !key.startsWith('default'))
-    );
-    // Strip description and columns from dataformTableConfig to avoid circular reference and bloat
-    if (configForDump.dataformTableConfig) {
-        const { description, columns, ...rest } = configForDump.dataformTableConfig;
-        configForDump.dataformTableConfig = rest;
-    }
-    const configJson = JSON.stringify(configForDump, null, 2);
-    sections.push(`The last full table refresh was done using this configuration:\n${configJson}`);
-
-    return sections.join('\n\n');
-};
-
-module.exports = {
-    getColumnDescriptions,
-    buildTableDescription,
-    composeDescription,
-    getLineageText,
-    buildConfigNotes,
-    isExcluded,
-};
+const constants = require('./constants');
+const { version } = require('./package.json');
+
+/**
+ * Composes a multi-section column description string from individual sections.
+ * Sections with null/undefined/empty values are omitted.
+ * Sections are separated by line breaks for readability.
+ *
+ * @param {Object} sections - { base, lineage, typicalUse, config }
+ * @returns {string} Composed description
+ */
+const composeDescription = (sections) => {
+    const parts = [];
+
+    if (sections.base) {
+        parts.push(sections.base);
+    }
+
+    if (sections.lineage) {
+        parts.push(`Lineage: ${sections.lineage}`);
+    }
+
+    if (sections.typicalUse) {
+        parts.push(`Typical use: ${sections.typicalUse}`);
+    }
+
+    if (sections.config) {
+        parts.push(`Config: ${sections.config}`);
+    }
+
+    return parts.join('\n\n');
+};
+
+/**
+ * Returns a formatted lineage text string for a column, or null if no lineage data exists.
+ *
+ * @param {string} columnName - The column name to look up.
+ * @param {Object} columnLineage - The lineage data object mapping column names to { source, note }.
+ * @returns {string|null} Formatted lineage string, e.g. "Derived -- Concatenation of ..."
+ */
+const getLineageText = (columnName, columnLineage) => {
+    const entry = columnLineage[columnName];
+    if (!entry) return null;
+
+    const sourceLabels = {
+        'ga4_export': 'Standard GA4 export field',
+        'ga4_export_modified': 'GA4 export field (modified)',
+        'derived': 'Derived',
+    };
+
+    const label = sourceLabels[entry.source] || entry.source;
+    return entry.note ? `${label} -- ${entry.note}` : label;
+};
+
+/**
+ * Builds a map of config-specific notes for columns based on the provided configuration.
+ * Extracts the configuration-dependent description suffixes into a { columnName: "note" } map.
+ *
+ * @param {Object} config - The merged configuration object.
+ * @returns {Object} Map of column names to config note strings.
+ */
+const buildConfigNotes = (config) => {
+    const notes = {};
+
+    if (!config) return notes;
+
+    const append = (key, text) => {
+        notes[key] = notes[key] ? `${notes[key]}. ${text}` : text;
+    };
+
+    // timezone
+    if (config.timezone) {
+        append('event_datetime', `Timezone: ${config.timezone}`);
+    }
+
+    // customTimestampParam
+    if (config.customTimestampParam) {
+        append('event_datetime', `Custom timestamp parameter: '${config.customTimestampParam}'`);
+        append('event_custom_timestamp', `Source parameter: '${config.customTimestampParam}'`);
+    }
+
+    // data_is_final
+    if (config.dataIsFinal) {
+        const method = config.dataIsFinal.detectionMethod;
+        if (method === 'DAY_THRESHOLD') {
+            append('data_is_final', `Detection method: DAY_THRESHOLD (${config.dataIsFinal.dayThreshold} days)`);
+        } else {
+            append('data_is_final', `Detection method: EXPORT_TYPE`);
+        }
+    }
+
+    // excludedEvents
+    if (config.excludedEvents && config.excludedEvents.length > 0) {
+        append('event_name', `Excluded events: ${config.excludedEvents.join(', ')}`);
+    }
+
+    // excludedEventParams
+    if (config.excludedEventParams && config.excludedEventParams.length > 0) {
+        append('event_params', `Excluded parameters: ${config.excludedEventParams.join(', ')}`);
+    }
+
+    // sessionParams
+    if (config.sessionParams && config.sessionParams.length > 0) {
+        append('session_params', `Configured parameters: ${config.sessionParams.join(', ')}`);
+    }
+
+    // includedExportTypes
+    if (config.includedExportTypes) {
+        const types = Object.entries(config.includedExportTypes)
+            .filter(([, enabled]) => enabled)
+            .map(([type]) => type);
+        if (types.length > 0) {
+            append('export_type', `Included export types: ${types.join(', ')}`);
+        }
+    }
+
+    return notes;
+};
+
+/**
+ * Returns a deep copy of the column descriptions, enriched with
+ * lineage, typical use, and configuration-specific sections composed into
+ * multi-section descriptions.
+ *
+ * @param {Object} config - The merged configuration object.
+ * @param {Object} columnMetadata - Column metadata provided by the table module.
+ * @param {Object} columnMetadata.descriptions - Column descriptions (Dataform ITableConfig columns format).
+ * @param {Object} columnMetadata.lineage - Column lineage data mapping column names to { source, note }.
+ * @param {Object} columnMetadata.typicalUse - Column typical use mapping column names to description strings.
+ * @returns {Object} Column descriptions object in Dataform ITableConfig columns format.
+ */
+const getColumnDescriptions = (config, columnMetadata) => {
+    const descriptions = JSON.parse(JSON.stringify(columnMetadata.descriptions));
+
+    const configNotes = buildConfigNotes(config);
+
+    // Compose multi-section descriptions for each top-level column
+    for (const key of Object.keys(descriptions)) {
+        const isStruct = typeof descriptions[key] === 'object' && descriptions[key].description;
+        const baseDesc = isStruct ? descriptions[key].description : (typeof descriptions[key] === 'string' ? descriptions[key] : null);
+
+        if (!baseDesc) continue;
+
+        const composed = composeDescription({
+            base: baseDesc,
+            lineage: getLineageText(key, columnMetadata.lineage),
+            typicalUse: columnMetadata.typicalUse[key] || null,
+            config: configNotes[key] || null,
+        });
+
+        if (isStruct) {
+            descriptions[key].description = composed;
+        } else {
+            descriptions[key] = composed;
+        }
+    }
+
+    // Add descriptions for dynamically promoted event parameter columns
+    if (config && config.eventParamsToColumns && config.eventParamsToColumns.length > 0) {
+        config.eventParamsToColumns.forEach(p => {
+            const columnName = p.columnName || p.name;
+            const type = p.type ? ` (${p.type})` : ' (any data type)';
+            descriptions[columnName] = composeDescription({
+                base: `Promoted from event parameter '${p.name}'${type}`,
+                lineage: `Derived -- Promoted from the event_params array`,
+                typicalUse: 'Promoted event parameter available as a top-level column for direct filtering and aggregation',
+                config: null,
+            });
+        });
+    }
+
+    // Add descriptions for columns added or replaced by data enrichments.
+    // Item-level enrichments are not yet supported and throw at SQL gen time — skip here.
+    if (config && Array.isArray(config.enrichments) && config.enrichments.length > 0) {
+        config.enrichments.forEach(e => {
+            const level = e.level ?? 'event';
+            if (level !== 'event') return;
+            const joinKeys = Array.isArray(e.joinKey) ? e.joinKey : [e.joinKey];
+            const joinKeyText = joinKeys.join(', ');
+            const sourceText = renderEnrichmentSource(e.source);
+            for (const c of e.columns) {
+                const existing = descriptions[c];
+                const existingText = typeof existing === 'string'
+                    ? existing
+                    : (existing && typeof existing === 'object' && existing.description)
+                        ? existing.description
+                        : null;
+                const newDesc = existingText
+                    ? `Coalesced by enrichment '${e.name}' (joined on ${joinKeyText} from ${sourceText}; falls back to original on missed JOIN). Original: ${existingText}`
+                    : `Added by enrichment '${e.name}' (joined on ${joinKeyText} from ${sourceText}).`;
+                // If the original was a struct-shaped entry, preserve the structure but replace the description.
+                // Otherwise, set as a plain string.
+                if (existing && typeof existing === 'object' && !Array.isArray(existing)) {
+                    descriptions[c] = { ...existing, description: newDesc };
+                } else {
+                    descriptions[c] = newDesc;
+                }
+            }
+        });
+    }
+
+    return descriptions;
+};
+
+/**
+ * Renders an enrichment source for inclusion in column descriptions.
+ *
+ * - Backtick-quoted string: passed through as-is.
+ * - Dataform table reference object: rendered as `<dataset>.<name>` (project not available
+ *   at description-generation time; resolved later via ctx.ref()).
+ *
+ * @param {string|Object} source - The enrichment's source field.
+ * @returns {string} Backtick-quoted source identifier for display.
+ */
+const renderEnrichmentSource = (source) => {
+    if (typeof source === 'string') return source;
+    if (source && typeof source === 'object') {
+        const dataset = source.dataset || source.schema;
+        if (dataset && source.name) return '`' + dataset + '.' + source.name + '`';
+    }
+    return String(source);
+};
+
+/**
+ * Checks whether a column (or its parent struct) is excluded by the config.
+ *
+ * @param {string[]} dependsOn - Column names this entry depends on.
+ * @param {string[]} excludedColumns - Combined excluded columns from config.
+ * @returns {boolean} True if ALL dependsOn columns are excluded.
+ */
+const isExcluded = (dependsOn, excludedColumns) => {
+    if (!dependsOn || dependsOn.length === 0) return false;
+    return dependsOn.every(col => excludedColumns.includes(col));
+};
+
+/**
+ * Builds the full table description by combining table-specific sections
+ * with shared sections (package attribution, config JSON dump).
+ *
+ * @param {Object} config - The merged configuration object.
+ * @param {string[]} tableSections - Table-specific description sections (provided by the table module).
+ * @returns {string} The composed table description.
+ */
+const buildTableDescription = (config, tableSections) => {
+    const sections = [...tableSections];
+
+    // Package Attribution
+    sections.push(`${constants.TABLE_DESCRIPTION_SUFFIX} Version: ${version}\n${constants.TABLE_DESCRIPTION_DOCUMENTATION_LINK}`);
+
+    // Config JSON dump
+    const configForDump = Object.fromEntries(
+        Object.entries(config).filter(([key]) => !key.startsWith('default'))
+    );
+    // Strip description and columns from dataformTableConfig to avoid circular reference and bloat
+    if (configForDump.dataformTableConfig) {
+        const { description, columns, ...rest } = configForDump.dataformTableConfig;
+        configForDump.dataformTableConfig = rest;
+    }
+    const configJson = JSON.stringify(configForDump, null, 2);
+    sections.push(`The last full table refresh was done using this configuration:\n${configJson}`);
+
+    return sections.join('\n\n');
+};
+
+module.exports = {
+    getColumnDescriptions,
+    buildTableDescription,
+    composeDescription,
+    getLineageText,
+    buildConfigNotes,
+    isExcluded,
+};