release: 发布 v0.6.2 DOCX 真实文档修复
新增能力:将 DOCX 发布验收拆分为四套独立 140,支持真实语料冻结、指纹复用、失败与基础设施错误独立统计,并为表格换行、全 JSON 围栏、代码连续性和长文档分页建立通用门禁。 问题修复:冻结 Paged.js 分片前的逻辑表格列轨并传递打印几何,统一 Markdown 表格换行、代码、段落与 OOXML 翻译;改进 PDF 文本流排序、语义块映射、颜色与栅格比较,消除窄字符重叠和跨行范围符号误报。 兼容与部署:版本统一为 0.6.2;正式 Docker 镜像内置固定 Chromium、Pandoc 3.9.0.2 和 Serif/Sans/Mono 字体;Desktop NSIS 与 ZIP 继续直接内置字体,无需系统字体安装。 验证结果:合成基线与长庆严格 280/280,M4N 140/140;健康数据残余误报 6/115(5.22%),均核查为重复表头自动对齐/取样误报且基础设施错误为 0。全项目测试、类型检查、生产构建和 git diff --check 通过;正式 Docker、NSIS、ZIP、离线镜像、部署包、清单及 SHA-256 均已生成并校验。
This commit is contained in:
@@ -98,6 +98,64 @@ local function replace_code_block(block)
|
||||
return pandoc.Para { image }
|
||||
end
|
||||
|
||||
local function preserve_raw_html_as_text(inline)
|
||||
if inline.format == "html" then
|
||||
return pandoc.Str(inline.text)
|
||||
end
|
||||
return inline
|
||||
end
|
||||
|
||||
local function preserve_raw_html_block_as_text(block)
|
||||
if block.format == "html" then
|
||||
return pandoc.Para { pandoc.Str(block.text) }
|
||||
end
|
||||
return block
|
||||
end
|
||||
|
||||
local function replace_table_breaks(table_block)
|
||||
return table_block:walk {
|
||||
RawInline = function(inline)
|
||||
if inline.format ~= "html" then
|
||||
return inline
|
||||
end
|
||||
local normalized = string.lower(inline.text)
|
||||
if normalized == "<br>"
|
||||
or normalized == "<br/>"
|
||||
or normalized == "<br />" then
|
||||
return pandoc.LineBreak()
|
||||
end
|
||||
return inline
|
||||
end
|
||||
}
|
||||
end
|
||||
|
||||
local function normalize_task_list(list)
|
||||
for _, item in ipairs(list.content) do
|
||||
local block = item[1]
|
||||
if block ~= nil and (block.t == "Plain" or block.t == "Para") then
|
||||
local inlines = block.content
|
||||
local first = inlines[1]
|
||||
if first ~= nil and first.t == "Str" then
|
||||
local marker = string.lower(first.text)
|
||||
if marker == "[x]" then
|
||||
first.text = "☒"
|
||||
elseif marker == "[" then
|
||||
local second = inlines[2]
|
||||
local third = inlines[3]
|
||||
if second ~= nil and second.t == "Space"
|
||||
and third ~= nil and third.t == "Str"
|
||||
and third.text == "]" then
|
||||
first.text = "☐"
|
||||
inlines:remove(3)
|
||||
inlines:remove(2)
|
||||
end
|
||||
end
|
||||
end
|
||||
end
|
||||
end
|
||||
return list
|
||||
end
|
||||
|
||||
local function append_inlines(target, value)
|
||||
target:extend(pandoc.Inlines(value))
|
||||
end
|
||||
@@ -167,7 +225,10 @@ local function validate_counts()
|
||||
error(
|
||||
"DOCX media map contains unused "
|
||||
.. kind
|
||||
.. " resources"
|
||||
.. " resources: consumed "
|
||||
.. tostring(counters[kind])
|
||||
.. " of "
|
||||
.. tostring(#media_map[kind])
|
||||
)
|
||||
end
|
||||
end
|
||||
@@ -176,8 +237,14 @@ end
|
||||
return {
|
||||
Pandoc = function(document)
|
||||
local transformed = document:walk {
|
||||
Table = replace_table_breaks
|
||||
}
|
||||
transformed = transformed:walk {
|
||||
Image = replace_image,
|
||||
CodeBlock = replace_code_block
|
||||
CodeBlock = replace_code_block,
|
||||
RawInline = preserve_raw_html_as_text,
|
||||
RawBlock = preserve_raw_html_block_as_text,
|
||||
BulletList = normalize_task_list
|
||||
}
|
||||
if structure_plan.titlePolicy.metadataTitle == "suppress" then
|
||||
transformed.meta.title = nil
|
||||
|
||||
Reference in New Issue
Block a user