@tiangong-lca/cli 0.0.18 → 0.0.21

package/README.md

@@ -17,8 +17,8 @@ checkPaths:
   - bin/**
   - src/cli.ts
   - src/main.ts
-lastReviewedAt: 2026-06-21
-lastReviewedCommit: 44fa7e3d01a9cb144184b0047770f82f0006cace
+lastReviewedAt: 2026-06-29
+lastReviewedCommit: 695e6d6fe718cb92d499f3ce8be2dc24c3f6ce29
 ---
 
 # TianGong LCA CLI

package/assets/tidas-schemas/tidas_processes.json

@@ -1414,18 +1414,38 @@
                     "description": "container tag for the specification of allocations if process has more than one reference product. Use only for multifunctional processes.",
                     "properties": {
                       "allocation": {
-                        "type": "object",
                         "description": "specifies one allocation of this exchange (see the attributes of this tag below)",
-                        "properties": {
-                          "@internalReferenceToCoProduct": {
-                            "$ref": "tidas_data_types.json#/$defs/Int6",
-                            "description": "Reference to one of the co-products. The applied allocation approach(es), details and and explanations are documented in the fields \"LCI method approaches\" and \"Deviations from LCI method approaches / explanations\". [Notes: Applicable only to multifunctional processes. The documented allocated fractions are only applicable when using the data set for attributional modelling and are to be ignored for consequential modeling.]"
+                        "anyOf": [
+                          {
+                            "type": "object",
+                            "properties": {
+                              "@internalReferenceToCoProduct": {
+                                "$ref": "tidas_data_types.json#/$defs/Int6",
+                                "description": "Reference to one of the co-products. The applied allocation approach(es), details and and explanations are documented in the fields \"LCI method approaches\" and \"Deviations from LCI method approaches / explanations\". [Notes: Applicable only to multifunctional processes. The documented allocated fractions are only applicable when using the data set for attributional modelling and are to be ignored for consequential modeling.]"
+                              },
+                              "@allocatedFraction": {
+                                "$ref": "tidas_data_types.json#/$defs/Perc",
+                                "description": "Fraction (expressed in %) of this Input or Output flow that is foreseen to be allocated to this co-product (recommended allocation). The numbers across the co-products should sum up to 100%."
+                              }
+                            }
                           },
-                          "@allocatedFraction": {
-                            "$ref": "tidas_data_types.json#/$defs/Perc",
-                            "description": "Fraction (expressed in %) of this Input or Output flow that is foreseen to be allocated to this co-product (recommended allocation). The numbers across the co-products should sum up to 100%."
+                          {
+                            "type": "array",
+                            "items": {
+                              "type": "object",
+                              "properties": {
+                                "@internalReferenceToCoProduct": {
+                                  "$ref": "tidas_data_types.json#/$defs/Int6",
+                                  "description": "Reference to one of the co-products. The applied allocation approach(es), details and and explanations are documented in the fields \"LCI method approaches\" and \"Deviations from LCI method approaches / explanations\". [Notes: Applicable only to multifunctional processes. The documented allocated fractions are only applicable when using the data set for attributional modelling and are to be ignored for consequential modeling.]"
+                                },
+                                "@allocatedFraction": {
+                                  "$ref": "tidas_data_types.json#/$defs/Perc",
+                                  "description": "Fraction (expressed in %) of this Input or Output flow that is foreseen to be allocated to this co-product (recommended allocation). The numbers across the co-products should sum up to 100%."
+                                }
+                              }
+                            }
                           }
-                        }
+                        ]
                       }
                     }
                   },

package/dist/src/cli.js

@@ -54,6 +54,7 @@ import { runDatasetPatchApply, } from './lib/dataset-patch.js';
 import { runDatasetSaveDraft, } from './lib/dataset-save-draft-run.js';
 import { runDatasetClassificationApply, runDatasetClassificationAudit, runDatasetClassificationChildren, runDatasetClassificationPath, } from './lib/dataset-classification.js';
 import { runDatasetMaintenanceClearAccount, } from './lib/dataset-maintenance-clear-account.js';
+import { runDatasetSourceUploadAttachments, } from './lib/dataset-source-upload-attachments.js';
 function renderMainHelp(dotEnvStatus) {
     return `TianGong LCA CLI
 
@@ -73,7 +74,7 @@ Implemented Commands:
   doctor     show environment diagnostics
   search     flow | process | lifecyclemodel
   process    get | list | identity-preflight | build-plan | scope-statistics | dedup-review | auto-build | resume-build | publish-build | complete-required-fields | save-draft | batch-build | refresh-references | verify-rows
-  dataset    contract get | context-pack | classification children/path/audit/apply | curation-queue build/next/verify | import-lca convert | author | patch apply | save-draft | validate | verify-remote | bilingual extract/apply/validate | evidence-search plan/run | references rewrite/refresh-remote | maintenance clear-account
+  dataset    contract get | context-pack | classification children/path/audit/apply | curation-queue build/next/verify | import-lca convert | author | patch apply | save-draft | source upload-attachments | validate | verify-remote | bilingual extract/apply/validate | evidence-search plan/run | references rewrite/refresh-remote | maintenance clear-account
   flow       get | list | identity-preflight | build-plan | fetch-rows | materialize-decisions | remediate | publish-version | publish-reviewed-data | build-alias-map | scan-process-flow-refs | plan-process-flow-repairs | apply-process-flow-repairs | regen-product | validate-processes
   lifecyclemodel auto-build | validate-build | publish-build | save-draft | graph | build-resulting-process | publish-resulting-process | orchestrate
   qa         process | flow | lifecyclemodel
@@ -268,6 +269,7 @@ Implemented Subcommands:
   author              Extract source evidence and prepare TIDAS context packs for AI authoring
   patch apply          Apply AI-authored structured dataset patches deterministically
   save-draft           Save contact/source/support or other canonical dataset rows through the platform dataset command path
+  source upload-attachments Upload source referenceToDigitalFile binaries to storage and rewrite their @uri
   validate             Validate local flow / process / lifecyclemodel rows with the TIDAS SDK
   verify-remote        Verify dataset roots and TIDAS references against remote published versions
   bilingual extract    Extract bilingual translation units from local rows
@@ -518,7 +520,7 @@ function renderDatasetImportLcaHelp() {
 Options:
   --input <path>          Source file, directory, or package to import
   --output-dir <dir>      Output directory for generated package and reports
-  --from-format <format>  auto, ecospold1, ecospold2, openlca-jsonld, openlca-process-xlsx, simapro-csv
+  --from-format <format>  auto, ecospold1, ecospold2, openlca-jsonld, openlca-process-xlsx, simapro-csv, ilcd
   --target <target>       tidas | ilcd | both (default: tidas)
   --report <file>         Conversion report path (default: <output-dir>/conversion-report.json)
   --mapping-dir <dir>     Optional custom mapping/reference data directory
@@ -644,6 +646,33 @@ Contract:
   Process and lifecyclemodel imports may still use their dedicated save-draft commands when the workflow needs their specialized reports.
 `.trim();
 }
+function renderDatasetSourceUploadAttachmentsHelp() {
+    return `Usage:
+  tiangong-lca dataset source upload-attachments --input <file|dir> --external-docs-dir <dir> [options]
+
+Uploads the binary documents referenced by source datasets via referenceToDigitalFile
+(e.g. "../external_docs/pef_method.pdf") to a Supabase Storage bucket using the current
+authenticated account session, then rewrites each source's referenceToDigitalFile @uri to
+"../<bucket>/<key>". Plain http(s) URIs are left untouched; backslash paths and filename
+case differences are normalized; each physical file is uploaded once (deduped).
+
+Options:
+  --input <file|dir>        Source TIDAS rows (.jsonl, .json, or a directory of *.json)
+  --external-docs-dir <dir> Directory holding the referenced binaries
+  --bucket <name>           Storage bucket (default: external_docs)
+  --out-dir <dir>           Artifact directory
+  --commit                  Upload binaries (default: dry-run plan only)
+  --dry-run                 Plan without uploading (default)
+  --verify                  After upload, create a signed URL to confirm each object resolves
+  --timeout-ms <n>          Per-request timeout (default: 30000)
+  --json                    Print compact JSON
+  -h, --help
+
+Outputs written under --out-dir:
+  - attachments-report.json
+  - rewritten-sources.jsonl
+`.trim();
+}
 function renderDatasetValidateHelp() {
     return `Usage:
   tiangong-lca dataset validate --input <file> [options]
@@ -2096,6 +2125,62 @@ function parseDatasetSaveDraftFlags(args) {
         allowReferenceOnlySupport: Boolean(values['allow-account-local-support']),
     };
 }
+function parseDatasetSourceUploadAttachmentsFlags(args) {
+    let values;
+    try {
+        ({ values } = parseArgs({
+            args,
+            allowPositionals: false,
+            strict: true,
+            options: {
+                help: { type: 'boolean', short: 'h' },
+                json: { type: 'boolean' },
+                input: { type: 'string' },
+                'external-docs-dir': { type: 'string' },
+                bucket: { type: 'string' },
+                'out-dir': { type: 'string' },
+                commit: { type: 'boolean' },
+                'dry-run': { type: 'boolean' },
+                verify: { type: 'boolean' },
+                'timeout-ms': { type: 'string' },
+            },
+        }));
+    }
+    catch (error) {
+        throw new CliError(String(error), {
+            code: 'INVALID_ARGS',
+            exitCode: 2,
+        });
+    }
+    if (values.commit && values['dry-run']) {
+        throw new CliError('Cannot pass both --commit and --dry-run.', {
+            code: 'INVALID_DATASET_SOURCE_UPLOAD_MODE',
+            exitCode: 2,
+        });
+    }
+    let timeoutMs;
+    if (typeof values['timeout-ms'] === 'string') {
+        const parsed = Number.parseInt(values['timeout-ms'], 10);
+        if (!Number.isInteger(parsed)) {
+            throw new CliError('--timeout-ms must be an integer.', {
+                code: 'INVALID_ARGS',
+                exitCode: 2,
+            });
+        }
+        timeoutMs = parsed;
+    }
+    return {
+        help: Boolean(values.help),
+        json: Boolean(values.json),
+        inputPath: typeof values.input === 'string' ? values.input : '',
+        externalDocsDir: typeof values['external-docs-dir'] === 'string' ? values['external-docs-dir'] : '',
+        bucket: typeof values.bucket === 'string' ? values.bucket : null,
+        outDir: typeof values['out-dir'] === 'string' ? values['out-dir'] : null,
+        commit: Boolean(values.commit),
+        verify: Boolean(values.verify),
+        timeoutMs,
+    };
+}
 function parseDatasetContractFlags(args) {
     let values;
     try {
@@ -4626,6 +4711,7 @@ export async function executeCli(argv, deps) {
         const datasetClassificationAuditImpl = deps.runDatasetClassificationAuditImpl ?? runDatasetClassificationAudit;
         const datasetClassificationApplyImpl = deps.runDatasetClassificationApplyImpl ?? runDatasetClassificationApply;
         const datasetMaintenanceClearAccountImpl = deps.runDatasetMaintenanceClearAccountImpl ?? runDatasetMaintenanceClearAccount;
+        const datasetSourceUploadAttachmentsImpl = deps.runDatasetSourceUploadAttachmentsImpl ?? runDatasetSourceUploadAttachments;
         if (flags.version) {
             return { exitCode: 0, stdout: `${loadCliPackageVersion(import.meta.url)}\n`, stderr: '' };
         }
@@ -4947,6 +5033,58 @@ export async function executeCli(argv, deps) {
                 stderr: '',
             };
         }
+        if (command === 'dataset' && subcommand === 'source') {
+            const action = commandArgs[0] ?? '';
+            if (!action || action === '--help' || action === '-h') {
+                return {
+                    exitCode: 0,
+                    stdout: `${renderDatasetSourceUploadAttachmentsHelp()}\n`,
+                    stderr: '',
+                };
+            }
+            if (action !== 'upload-attachments') {
+                throw new CliError("dataset source action must be 'upload-attachments'.", {
+                    code: 'DATASET_SOURCE_ACTION_INVALID',
+                    exitCode: 2,
+                });
+            }
+            const datasetFlags = parseDatasetSourceUploadAttachmentsFlags(commandArgs.slice(1));
+            if (datasetFlags.help) {
+                return {
+                    exitCode: 0,
+                    stdout: `${renderDatasetSourceUploadAttachmentsHelp()}\n`,
+                    stderr: '',
+                };
+            }
+            if (!datasetFlags.inputPath) {
+                throw new CliError('dataset source upload-attachments requires --input.', {
+                    code: 'DATASET_SOURCE_UPLOAD_INPUT_REQUIRED',
+                    exitCode: 2,
+                });
+            }
+            if (!datasetFlags.externalDocsDir) {
+                throw new CliError('dataset source upload-attachments requires --external-docs-dir.', {
+                    code: 'DATASET_SOURCE_UPLOAD_EXTERNAL_DOCS_DIR_REQUIRED',
+                    exitCode: 2,
+                });
+            }
+            const report = await datasetSourceUploadAttachmentsImpl({
+                inputPath: datasetFlags.inputPath,
+                externalDocsDir: datasetFlags.externalDocsDir,
+                bucket: datasetFlags.bucket,
+                outDir: datasetFlags.outDir,
+                commit: datasetFlags.commit,
+                verify: datasetFlags.verify,
+                timeoutMs: datasetFlags.timeoutMs,
+                env: deps.env,
+                fetchImpl: deps.fetchImpl,
+            });
+            return {
+                exitCode: report.status === 'completed_with_failures' ? 1 : 0,
+                stdout: stringifyJson(report, datasetFlags.json),
+                stderr: '',
+            };
+        }
         if (command === 'dataset' && subcommand === 'save-draft') {
             const datasetFlags = parseDatasetSaveDraftFlags(commandArgs);
             if (datasetFlags.help) {