Compare commits

...

1 Commits

Author SHA1 Message Date
zhanghuanxu
a84fe91fa1 feat: support PDF imports as slides 2026-06-10 14:13:02 +08:00
7 changed files with 105 additions and 14 deletions

View File

@@ -27,7 +27,7 @@ var DriveImport = common.Shortcut{
},
AuthTypes: []string{"user", "bot"},
Flags: []common.Flag{
{Name: "file", Desc: "local file path (e.g. .docx, .xlsx, .md, .base, .pptx; large files auto use multipart upload; .base is capped at 20MB, .pptx at 500MB)", Required: true},
{Name: "file", Desc: "local file path (e.g. .docx, .xlsx, .md, .base, .pptx, .pdf; large files auto use multipart upload; .base is capped at 20MB, .pptx/.pdf at 500MB)", Required: true},
{Name: "type", Desc: "target document type (docx, sheet, bitable, slides)", Required: true},
{Name: "folder-token", Desc: "target folder token (omit for root folder; API accepts empty mount_key as root)"},
{Name: "name", Desc: "imported file name (default: local file name without extension)"},

View File

@@ -45,6 +45,7 @@ var driveImportExtToDocTypes = map[string][]string{
"csv": {"sheet", "bitable"},
"base": {"bitable"},
"pptx": {"slides"},
"pdf": {"slides"},
}
// driveImportSpec contains the user-facing import inputs after normalization.
@@ -153,7 +154,7 @@ func driveImportFileSizeLimit(filePath, docType string) (int64, bool) {
switch strings.TrimPrefix(strings.ToLower(filepath.Ext(filePath)), ".") {
case "docx", "doc":
return driveImport600MBFileSizeLimit, true
case "pptx":
case "pptx", "pdf":
return driveImport500MBFileSizeLimit, true
case "txt", "md", "mark", "markdown", "html", "xls", "base":
return driveImport20MBFileSizeLimit, true
@@ -199,7 +200,7 @@ func validateDriveImportFileSize(filePath, docType string, fileSize int64) error
func validateDriveImportSpec(spec driveImportSpec) error {
ext := spec.FileExtension()
if ext == "" {
return errs.NewValidationError(errs.SubtypeInvalidArgument, "file must have an extension (e.g. .md, .docx, .xlsx, .pptx)").WithParam("--file")
return errs.NewValidationError(errs.SubtypeInvalidArgument, "file must have an extension (e.g. .md, .docx, .xlsx, .pptx, .pdf)").WithParam("--file")
}
switch spec.DocType {
@@ -210,7 +211,7 @@ func validateDriveImportSpec(spec driveImportSpec) error {
supportedTypes, ok := driveImportExtToDocTypes[ext]
if !ok {
return errs.NewValidationError(errs.SubtypeInvalidArgument, "unsupported file extension: %s. Supported extensions are: docx, doc, txt, md, mark, markdown, html, xlsx, xls, csv, base, pptx", ext).WithParam("--file")
return errs.NewValidationError(errs.SubtypeInvalidArgument, "unsupported file extension: %s. Supported extensions are: docx, doc, txt, md, mark, markdown, html, xlsx, xls, csv, base, pptx, pdf", ext).WithParam("--file")
}
typeAllowed := false
@@ -231,8 +232,8 @@ func validateDriveImportSpec(spec driveImportSpec) error {
hint = fmt.Sprintf(".xls files can only be imported as 'sheet', not '%s'", spec.DocType)
case "base":
hint = fmt.Sprintf(".base files can only be imported as 'bitable', not '%s'", spec.DocType)
case "pptx":
hint = fmt.Sprintf(".pptx files can only be imported as 'slides', not '%s'", spec.DocType)
case "pptx", "pdf":
hint = fmt.Sprintf(".%s files can only be imported as 'slides', not '%s'", ext, spec.DocType)
default:
hint = fmt.Sprintf(".%s files can only be imported as 'docx', not '%s'", ext, spec.DocType)
}

View File

@@ -39,6 +39,10 @@ func TestValidateDriveImportSpec(t *testing.T) {
name: "pptx slides ok",
spec: driveImportSpec{FilePath: "./deck.pptx", DocType: "slides"},
},
{
name: "pdf slides ok",
spec: driveImportSpec{FilePath: "./deck.pdf", DocType: "slides"},
},
{
name: "base non bitable rejected",
spec: driveImportSpec{FilePath: "./snapshot.base", DocType: "sheet"},
@@ -49,6 +53,11 @@ func TestValidateDriveImportSpec(t *testing.T) {
spec: driveImportSpec{FilePath: "./deck.pptx", DocType: "docx"},
wantErr: ".pptx files can only be imported as 'slides'",
},
{
name: "pdf non slides rejected",
spec: driveImportSpec{FilePath: "./deck.pdf", DocType: "docx"},
wantErr: ".pdf files can only be imported as 'slides'",
},
{
name: "unknown extension rejected",
spec: driveImportSpec{FilePath: "./data.rtf", DocType: "docx"},
@@ -136,6 +145,19 @@ func TestValidateDriveImportFileSize(t *testing.T) {
docType: "slides",
fileSize: driveImport500MBFileSizeLimit,
},
{
name: "pdf exceeds 500mb limit",
filePath: "./deck.pdf",
docType: "slides",
fileSize: driveImport500MBFileSizeLimit + 1,
wantText: "exceeds 500.0 MB import limit for .pdf",
},
{
name: "pdf within 500mb limit",
filePath: "./deck.pdf",
docType: "slides",
fileSize: driveImport500MBFileSizeLimit,
},
{
name: "base exceeds 20mb limit",
filePath: "./snapshot.base",

View File

@@ -2,7 +2,7 @@
> **前置条件:** 先阅读 [`../lark-shared/SKILL.md`](../../lark-shared/SKILL.md) 了解认证、全局参数和安全规则。
将本地文件(如 Word、TXT、Markdown、Excel、PPTX 等导入并转换为飞书在线云文档docx、sheet、bitable、slides。底层统一通过 `POST /open-apis/drive/v1/import_tasks` 接口创建导入任务,并在 shortcut 内做有限次数轮询 `GET /open-apis/drive/v1/import_tasks/:ticket`
将本地文件(如 Word、TXT、Markdown、Excel、PPTX、PDF导入并转换为飞书在线云文档docx、sheet、bitable、slides。底层统一通过 `POST /open-apis/drive/v1/import_tasks` 接口创建导入任务,并在 shortcut 内做有限次数轮询 `GET /open-apis/drive/v1/import_tasks/:ticket`
> [!IMPORTANT]
> 当用户说“把本地 Excel / CSV / `.base` 快照导入成 Base / 多维表格 / bitable 文档”时,第一步必须使用 `drive +import --type bitable`。
@@ -40,8 +40,9 @@ lark-cli drive +import --file ./crm.xlsx --type bitable --name "客户台账"
# 导入 .base 快照为多维表格 / Base (bitable)(文件不能超过 20MB
lark-cli drive +import --file ./snapshot.base --type bitable --name "快照还原"
# 导入 PPTX 为飞书幻灯片 (slides)(文件不能超过 500MB
# 导入 PPTX / PDF 为飞书幻灯片 (slides)(文件不能超过 500MB
lark-cli drive +import --file ./deck.pptx --type slides --name "项目汇报"
lark-cli drive +import --file ./deck.pdf --type slides --name "项目汇报"
# 导入到指定文件夹,并指定导入后的文件名
lark-cli drive +import --file ./data.csv --type bitable --folder-token <FOLDER_TOKEN> --name "导入数据表"
@@ -89,6 +90,7 @@ lark-cli drive +import --file ./README.md --type docx --dry-run
| `.csv` | `sheet`, `bitable` | CSV 数据文件 |
| `.base` | `bitable` | 多维表格快照文件 |
| `.pptx` | `slides` | Microsoft PowerPoint 演示文稿 |
| `.pdf` | `slides` | PDF 文档 |
> [!IMPORTANT]
> 用户口头说的 “Base” / “多维表格” / “bitable”在命令里统一对应 `--type bitable`。
@@ -98,7 +100,7 @@ lark-cli drive +import --file ./README.md --type docx --dry-run
> - `.xlsx` / `.csv` 文件**只能**导入为 `sheet` 或 `bitable`
> - `.xls` 文件**只能**导入为 `sheet`
> - `.base` 文件**只能**导入为 `bitable`
> - `.pptx` 文件**只能**导入为 `slides`
> - `.pptx` / `.pdf` 文件**只能**导入为 `slides`
> - 例如:`.csv` 文件不能导入为 `docx``.md` 文件不能导入为 `sheet`
> [!IMPORTANT]
@@ -132,7 +134,7 @@ lark-cli drive +import --file ./README.md --type docx --dry-run
| `.csv` | `bitable` | 100MB |
| `.xls` | `sheet` | 20MB |
| `.base` | `bitable` | 20MB |
| `.pptx` | `slides` | 500MB |
| `.pptx`, `.pdf` | `slides` | 500MB |
- 如果文件超出对应上限shortcut 会在真正上传前直接返回验证错误。
- “超过 20MB 自动切换分片上传”只表示上传链路会切到 multipart不代表所有格式都允许导入超过 20MB 的文件。

View File

@@ -1,7 +1,7 @@
---
name: lark-slides
version: 1.0.0
description: "飞书幻灯片:创建和编辑幻灯片。创建演示文稿、读取幻灯片内容、管理幻灯片页面(创建、删除、读取、局部替换)。当用户需要创建或编辑幻灯片、读取或修改单个页面时使用。当用户给出 doubao.com 的 /slides/ URL/token 时,也应直接使用本 skill不要因为域名不是飞书而回退到 WebFetch路由依据是 URL 路径模式和 token而不是域名。不负责云文档内容编辑走 lark-doc、云文档里的独立画板对象走 lark-whiteboard注意 slide 内嵌的流程图/架构图仍属本 skill、上传或下载普通文件走 lark-drive。"
description: "飞书幻灯片:创建和编辑幻灯片。创建演示文稿、读取幻灯片内容、管理幻灯片页面(创建、删除、读取、局部替换)。当用户需要创建或编辑幻灯片、读取或修改单个页面时使用。当用户给出 doubao.com 的 /slides/ URL/token 时,也应直接使用本 skill不要因为域名不是飞书而回退到 WebFetch路由依据是 URL 路径模式和 token而不是域名。不负责本地 `.pptx` / `.pdf` 导入为 slides`lark-drive``drive +import --type slides`)、云文档内容编辑(走 lark-doc、云文档里的独立画板对象走 lark-whiteboard注意 slide 内嵌的流程图/架构图仍属本 skill、上传或下载普通文件走 lark-drive。"
metadata:
requires:
bins: ["lark-cli"]

View File

@@ -2,8 +2,8 @@
## Metrics
- Denominator: 31 leaf commands
- Covered: 10
- Coverage: 32.3%
- Covered: 11
- Coverage: 35.5%
## Summary
- TestDrive_FilesCreateFolderWorkflow: proves `drive files create_folder` in `create_folder as bot`; helper asserts the returned folder token and registers best-effort cleanup via `drive files delete`.
@@ -15,6 +15,7 @@
- TestDriveAddCommentMarkdownFileWorkflow: opt-in live workflow skeleton for the same path, gated by `LARK_DRIVE_MD_COMMENT_E2E=1`.
- TestDrive_SecureLabelDryRun: dry-run coverage for `drive +secure-label-list` and `drive +secure-label-update`; asserts label-list query params and update URL→type inference, request method/URL/type query, and `label-id` body shape. Runs without hitting live APIs because update can trigger document-level security approval flows.
- TestDriveExportDryRun_FileNameMetadata: dry-run coverage for `drive +export`; asserts export task request shape and local `--file-name` / `--output-dir` metadata without calling live APIs.
- TestDriveImportDryRun_PDFToSlides: dry-run coverage for `drive +import`; asserts PDF-to-slides request shape across media upload `extra` and import task body without calling live APIs.
- TestDrive_PullDryRun / TestDrive_PullDryRunAcceptsDuplicateRemoteStrategies: dry-run coverage for `drive +pull`; asserts the list-files request shape, Validate-stage safety guards, and acceptance of `--on-duplicate-remote=rename|newest|oldest` by the real CLI binary.
- TestDrive_PushDryRun / TestDrive_PushDryRunAcceptsDuplicateRemoteStrategies: dry-run coverage for `drive +push`; asserts the list-files request shape, Validate-stage safety guards, conditional delete preflight, and acceptance of `--on-duplicate-remote=newest|oldest` by the real CLI binary.
- Cleanup note: `drive files delete` is only exercised in cleanup and is intentionally left uncovered.
@@ -31,7 +32,7 @@
| ✕ | drive +download | shortcut | | none | no file fixture workflow yet |
| ✓ | drive +export | shortcut | drive_export_dryrun_test.go::TestDriveExportDryRun_FileNameMetadata | `--token`; `--doc-type`; `--file-extension`; `--file-name`; `--output-dir` | dry-run only; no live export workflow yet |
| ✕ | drive +export-download | shortcut | | none | no export-download workflow yet |
| | drive +import | shortcut | | none | no import workflow yet |
| | drive +import | shortcut | drive_import_dryrun_test.go::TestDriveImportDryRun_PDFToSlides | `.pdf` source with `--type slides`; media upload `extra.file_extension=pdf`; import task `file_extension=pdf`, `type=slides`, `file_name` | dry-run only; no live import workflow yet |
| ✕ | drive +move | shortcut | | none | no move workflow yet |
| ✓ | drive +pull | shortcut | drive_pull_dryrun_test.go::TestDrive_PullDryRun + drive_duplicate_sync_workflow_test.go::TestDrive_DuplicateRemoteWorkflow | `--local-dir`; `--folder-token`; `--on-duplicate-remote=rename\|newest\|oldest`; `--delete-local --yes` guard | dry-run locks flag/validate shape; live workflow proves duplicate fail-fast and rename recovery |
| ✓ | drive +push | shortcut | drive_push_dryrun_test.go::TestDrive_PushDryRun + drive_duplicate_sync_workflow_test.go::TestDrive_DuplicateRemoteWorkflow | `--local-dir`; `--folder-token`; `--if-exists`; `--on-duplicate-remote=newest\|oldest`; `--delete-remote --yes` | dry-run locks flag/validate shape; live workflow proves overwrite + duplicate cleanup converges status |

View File

@@ -0,0 +1,65 @@
// Copyright (c) 2026 Lark Technologies Pte. Ltd.
// SPDX-License-Identifier: MIT
package drive
import (
"context"
"os"
"path/filepath"
"testing"
"time"
clie2e "github.com/larksuite/cli/tests/cli_e2e"
"github.com/stretchr/testify/require"
"github.com/tidwall/gjson"
)
func TestDriveImportDryRun_PDFToSlides(t *testing.T) {
setDriveDryRunConfigEnv(t)
tmpDir := t.TempDir()
if err := os.WriteFile(filepath.Join(tmpDir, "deck.pdf"), []byte("%PDF-1.7\n"), 0o644); err != nil {
t.Fatalf("WriteFile() error: %v", err)
}
ctx, cancel := context.WithTimeout(context.Background(), 30*time.Second)
t.Cleanup(cancel)
result, err := clie2e.RunCmd(ctx, clie2e.Request{
Args: []string{
"drive", "+import",
"--file", "./deck.pdf",
"--type", "slides",
"--name", "pdf-deck",
"--dry-run",
},
DefaultAs: "bot",
WorkDir: tmpDir,
})
require.NoError(t, err)
result.AssertExitCode(t, 0)
out := result.Stdout
if got := gjson.Get(out, "api.0.url").String(); got != "/open-apis/drive/v1/medias/upload_all" {
t.Fatalf("upload url=%q, want upload_all\nstdout:\n%s", got, out)
}
if got := gjson.Get(out, "api.0.body.file_name").String(); got != "deck.pdf" {
t.Fatalf("upload file_name=%q, want deck.pdf\nstdout:\n%s", got, out)
}
if got := gjson.Get(out, "api.0.body.extra").String(); got != `{"file_extension":"pdf","obj_type":"slides"}` {
t.Fatalf("upload extra=%q, want pdf/slides extra\nstdout:\n%s", got, out)
}
if got := gjson.Get(out, "api.1.url").String(); got != "/open-apis/drive/v1/import_tasks" {
t.Fatalf("import url=%q, want import_tasks\nstdout:\n%s", got, out)
}
if got := gjson.Get(out, "api.1.body.file_extension").String(); got != "pdf" {
t.Fatalf("body.file_extension=%q, want pdf\nstdout:\n%s", got, out)
}
if got := gjson.Get(out, "api.1.body.type").String(); got != "slides" {
t.Fatalf("body.type=%q, want slides\nstdout:\n%s", got, out)
}
if got := gjson.Get(out, "api.1.body.file_name").String(); got != "pdf-deck" {
t.Fatalf("body.file_name=%q, want pdf-deck\nstdout:\n%s", got, out)
}
}