使用graphviz画数据结构

• 1 Graphviz & graphviz-dot-mode
  • 1.1 What is Graphviz?
  • 1.2 Graphviz 的安装
  • 1.3 Graphviz 的使用
  • 1.4 graphviz-dot-mode
• 2 小函数登场
  • 2.1 elisp 代码
  • 2.2 使用方法
• 3 autoinert 配置
• 4 用法示例
• 5 后记

1.1 What is Graphviz?

1.2 Graphviz 的安装

emerge -av graphviz

1.3 Graphviz 的使用

1.4 graphviz-dot-mode

emerge -av graphivz-dot-mode

(load "graphviz-dot-mode.el" nil t t)
 
(add-hook 'find-file-hook (lambda()
                            (if (string= "dot" (file-name-extension
                                                buffer-file-name))
                                (progn
                                  (message "Enabling Setings for dot-mode")
                                  (setq fill-column 1000)
                                  (base-auto-pair)
                                  (local-set-key (kbd "<C-f6>") 'compile)
                                  )
                              )))

2.1 elisp 代码

;; Function used to add fields of struct into a dot file (for Graphviz).
(defconst yyc/dot-head "subgraph cluster_%s {
    node [shape=record fontsize=12 fontname=Courier style=filled];
    color = lightgray;
    style=filled;
    label = \"Struct %s\";
    edge[color=\"#2e3436\"];"
  "Header part of dot file.")
(defconst yyc/dot-tail "
}"
  "Tail part of dot")
(defconst yyc/dot-node-head
  "
        node_%s[shape=record label=\"<f0>*** STRUCT %s ***|\\"
  "Format of node.")
(defconst yyc/dot-node-tail "
\"];"
  "Format of node.")
 
(defconst r_attr_str "[ \t]+\\(.*+\\)[ \t]+\\(.*\\)?;"
  "Regular expression for matching struct fields.")
 
(defconst r_name "\\_<\\(typedef[ \t]+\\)?struct[ \t]+\\(.*\\)?[ \t]*{"
  "Regular expression for mating struct name")
 
(defconst attr_str "
<f%d>%s %s\\l|\\" "nil")
 
(defun yyc/datastruct-to-dot (start end)
  "generate c++ function definition and insert it into `buffer'"
  (interactive "rp")
  (setq var-defination (buffer-substring-no-properties start end))
  (let* ((tmp_str "")
         (var-name "")
         (var-type "")
         (counter 0)
         (struct-name "")
         (header-str "")
         )
    (defun iter (pos)
      (setq counter (+ counter 1))
      (message (format "Counter: %d, pos: %d"
                       counter pos))
      (if (string-match r_name var-defination pos)
          (progn
            (message "A")
            (setq struct-name
                  (match-string 2 var-defination))
            (setq header-str
                  (format yyc/dot-head struct-name struct-name))
            (setq tmp_str
                  (format yyc/dot-node-head struct-name struct-name))
            (iter (match-end 0)))
        (if (string-match r_attr_str var-defination pos)
            (progn
              (message "B")
              (setq var-type
                    (match-string 1 var-defination))
              (setq var-name
                    (match-string 2 var-defination))
              (setq tmp_str
                    (concat tmp_str
                            (format attr_str counter var-type var-name)))
              (iter (match-end 0)))
          nil)))
    (save-excursion
      (iter 0)
      (set-buffer (get-buffer-create "tmp.dot"))
      (graphviz-dot-mode)
      (setq pos (point-max))
      (insert  header-str tmp_str )
      (goto-char (point-max))
      (delete-char -1)
      (insert "<f999>\\"yyc/dot-node-tail yyc/dot-tail)
      )
    (if (one-window-p)
        (split-window-vertically))
    (switch-to-buffer-other-window "tmp.dot")
    (goto-char (point-min))
    )
  (message "Finished, please see *tmp.dot* buffer.")
  )

2.2 使用方法

auto-insert 是 Emacs 自带的功能，稍加配置即可使用：

 ;; ************** Autoinsert templates *****************
(require 'autoinsert)
(setq auto-insert-mode t)  ;;; Adds hook to find-files-hook
(setq auto-insert-directory "~/.emacs.d/templates/auto-insert/")
(setq auto-insert 'other)
(setq auto-insert-query nil)
 
;; auto-insert stuff
(add-hook 'find-file-hooks 'auto-insert)
(setq auto-insert-alist
      '(
        ("\\.cpp$" . ["insert.cpp" auto-update-c-source-file])
        ("\\.h$"   . ["header.h" auto-update-header-file])
        ("\\.c$" . ["insert.c" auto-update-c-source-file])
        ("\\.org$" . ["insert.org" auto-update-defaults])
        ("\\.sh$" . ["insert.sh" auto-update-defaults])
        ("\\.lisp$" . ["insert.lisp" auto-update-defaults])
        ("\\.el$" . ["insert.el" auto-update-defaults])
        ("\\.dot$" . ["insert.dot" auto-update-defaults])
        ("\\.erl$" . ["insert.err" auto-update-defaults])
        ("\\.py$" . ["insert.py" auto-update-defaults])
        ("\\.tex$" . ["insert.tex" auto-update-defaults])
        ("\\.html$" . ["insert.html" auto-update-defaults])
        ("\\.devhelp2$" . ["insert.devhelp2" auto-update-defaults])
        ("\\.ebuild$" . ["insert.ebuild" auto-update-defaults])
        ("\\.sh$" . ["insert.sh" auto-update-defaults])
        ("Doxyfile$" . ["insert.doxyfile" auto-update-defaults])
        ))
 
;; function replaces the string '@@@' by the current file
;; name. You could use a similar approach to insert name and date into
;; your file.
(defun auto-update-header-file ()
  (save-excursion
    (while (search-forward "@@@" nil t)
      (save-restriction
        (narrow-to-region (match-beginning 0) (match-end 0))
        (replace-match (upcase (file-name-nondirectory buffer-file-name)))
        (subst-char-in-region (point-min) (point-max) ?. ?_)
        ))
    )
  )
 
(defun insert-today ()
  "Insert today's date into buffer"
  (interactive)
  (insert (format-time-string "%m-%e-%Y" (current-time))))
 
(defun auto-update-c-source-file ()
  (save-excursion
    ;; Replace HHHH with file name sans suffix
    (while (search-forward "HHHH" nil t)
      (save-restriction
        (narrow-to-region (match-beginning 0) (match-end 0))
        (replace-match (concat (file-name-sans-extension (file-name-nondirectory buffer-file-name)) ".h") t
                       )
        ))
    )
  (save-excursion
    ;; Replace @@@ with file name
    (while (search-forward "@@@" nil t)
      (save-restriction
        (narrow-to-region (match-beginning 0) (match-end 0))
        (replace-match (file-name-nondirectory buffer-file-name))
        ))
    )
  (save-excursion
    ;; replace DDDD with today's date
    (while (search-forward "DDDD" nil t)
      (save-restriction
        (narrow-to-region (match-beginning 0) (match-end 0))
        (replace-match "")
        (insert-today)
        ))
    )
  )
 
(defun auto-replace-file-name ()
  (save-excursion
    ;; Replace @@@ with file name
    (while (search-forward "(>>FILE<<)" nil t)
      (save-restriction
        (narrow-to-region (match-beginning 0) (match-end 0))
        (replace-match (file-name-nondirectory buffer-file-name) t)
        ))
    )
  )
 
(defun auto-update-defaults ()
  (auto-replace-file-name)
  (auto-replace-file-name-no-ext)
  (auto-replace-date-time)
  )
 
(defun auto-replace-file-name-no-ext ()
  (save-excursion
    ;; Replace @@@ with file name
    (while (search-forward "(>>FILE_NO_EXT<<)" nil t)
      (save-restriction
        (narrow-to-region (match-beginning 0) (match-end 0))
        (replace-match (file-name-sans-extension (file-name-nondirectory buffer-file-name)) t)
        ))
    )
  )
 
(defun auto-replace-date-time ()
  (save-excursion
    (while (search-forward "(>>DATE<<)" nil t)
      (save-restriction
        (narrow-to-region (match-beginning 0) (match-end 0))
        (replace-match "" t)
        (insert-today)
        ))))

模板文件存放于 “~/.emacs.d/templates/auto-insert/” 中，其中， insert.dot 的内容如下：

// $Id: (>>FILE<<), (>>DATE<<)
digraph Name {
    node [shape=record fontsize=12 fontname=Courier style=filled];
    edge[color=blue];
    rankdir=LR;

// XXX: place to put subgraph

}

一个简单的使用示例，有如下步骤：

• 1: 打开一个 C 文件
  

  如内核代码中的 drivers/usb/storage/usb.h

• 2: 打开一个 dot 文件(/tmp/usb.dot)
  

  auto-insert 会自动插入一些文件内容.

• 3: 选中 struct us_data 的定义，并执行 yyc/datastruct-to-dot。
  

  执行完成后， us_data 的数据填写到了 tmp.dot 中，将该 buffer 中的所有内容 kill 掉，并 yank 到 usb.dot 中 XXX 这一行的下面。此时，保存 sub.dot ， 并按下快捷键 : C-cc ， 然后按下 Enter ， 就会自动编译。然后再按下 C-cp 就可以在另外一个 buffer 中预览它了。

  其实到这里，一个 C 语言的 struct 数据结构就已经被画出来了，后面的两个步骤，是为了介绍怎样将多个数据结构联系起来。

• 4: 添加其他的 subgraph
  

  我们可以继续添加其他的 subgraph ， 例如 struct usb_ctrlrequest *cr ，以及 struct usb_sg_request， 并全部做为 subgraph 添加到 usb.dot 中。

• 5: 为 subgraph 建立关联
  

  很简单，通过 “->” 画两条线就可以了。

  最后生成的文件如下：

  digraph USB {
      node [shape=record fontsize=12 fontname=Courier style=filled];
      edge[color=blue];
      rankdir=LR;
  
  subgraph cluster_us_data  {
      node [shape=record fontsize=12 fontname=Courier style=filled];
      color = lightgray;
      style=filled;
      label = "Struct us_data ";
      edge[color="#2e3436"];
          node_us_data [shape=record label="<f0>*** STRUCT us_data  ***|\
  <f2>struct mutex     dev_mutex\l|\
  <f3>struct usb_device *pusb_dev\l|\
  <f4>struct usb_interface *pusb_intf\l|\
  <f5>struct us_unusual_dev   *unusual_dev\l|\
  <f6>unsigned long    fflags\l|\
  <f7>unsigned long    dflags\l|\
  <f8>unsigned int     send_bulk_pipe\l|\
  <f9>unsigned int     recv_bulk_pipe\l|\
  <f10>unsigned int    send_ctrl_pipe\l|\
  <f11>unsigned int    recv_ctrl_pipe\l|\
  <f12>unsigned int    recv_intr_pipe\l|\
  <f13>char        *transport_name\l|\
  <f14>char        *protocol_name\l|\
  <f15>__le32      bcs_signature\l|\
  <f16>u8      subclass\l|\
  <f17>u8      protocol\l|\
  <f18>u8      max_lun\l|\
  <f19>u8      ifnum\l|\
  <f20>u8      ep_bInterval\l|\
  <f21>trans_cmnd  transport\l|\
  <f22>trans_reset     transport_reset\l|\
  <f23>proto_cmnd  proto_handler\l|\
  <f24>struct scsi_cmnd *srb\l|\
  <f25>unsigned int    tag\l|\
  <f26>char        scsi_name[32]\l|\
  <f27>struct urb  *current_urb\l|\
  <f28>struct usb_ctrlrequest *cr\l|\
  <f29>struct usb_sg_request current_sg\l|\
  <f30>unsigned char   *iobuf\l|\
  <f31>dma_addr_t  iobuf_dma\l|\
  <f32>struct task_struct *ctl_thread\l|\
  <f33>struct completion cmnd_ready\l|\
  <f34>struct completion notify\l|\
  <f35>wait_queue_head_t delay_wait\l|\
  <f36>struct completion scanning_done\l|\
  <f37>void        *extra\l|\
  <f38>extra_data_destructor extra_destructor\l|\
  <f39>pm_hook         suspend_resume_hook\l|\
  <f40>int         use_last_sector_hacks\l|\
  <f41>int         last_sector_retries\l|<f999>\
  "];
  }
  
  subgraph cluster_usb_ctrlrequest  {
      node [shape=record fontsize=12 fontname=Courier style=filled];
      color = lightgray;
      style=filled;
      label = "Struct usb_ctrlrequest ";
      edge[color="#2e3436"];
          node_usb_ctrlrequest [shape=record label="<f0>*** STRUCT usb_ctrlrequest  ***|\
  <f2>__u8 bRequestType\l|\
  <f3>__u8 bRequest\l|\
  <f4>__le16 wValue\l|\
  <f5>__le16 wIndex\l|\
  <f6>__le16 wLength\l|<f999>\
  "];
  }
  
  subgraph cluster_usb_sg_request  {
      node [shape=record fontsize=12 fontname=Courier style=filled];
      color = lightgray;
      style=filled;
      label = "Struct usb_sg_request ";
      edge[color="#2e3436"];
          node_usb_sg_request [shape=record label="<f0>*** STRUCT usb_sg_request  ***|\
  <f2>int      status\l|\
  <f3>size_t       bytes\l|\
  <f4>spinlock_t   lock\l|\
  <f5>struct usb_device *dev\l|\
  <f6>int      pipe\l|\
  <f7>int      entries\l|\
  <f8>struct urb   **urbs\l|\
  <f9>int      count\l|\
  <f10>struct completion complete\l|<f999>\
  "];
  }
  
  node_us_data:f28 -> node_usb_ctrlrequest:f0;
  node_us_data:f29 -> node_usb_sg_request:f0[color=brown];
  node_us_data:f29 -> node_usb_sg_request:f999[color=brown];
  
  }
  

  生成的图下如下：
  

  

  graphviz ds

功能上还有很多地方可以改进，比如通过 CEDET 的 Semantic 进行语义分析，参考 corge 代码，支持 C++ 中的 class 等等。以后有时间在改改。PS: 貌似写这个 blog 用的时间比写那个 elisp 代码更费时间 ……